diff --git a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java index 7f29da2..86eded3 100644 --- a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java +++ b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java @@ -744,7 +744,7 @@ public void setSparkConfigUpdated(boolean isSparkConfigUpdated) { // CBO related HIVE_CBO_ENABLED("hive.cbo.enable", true, "Flag to control enabling Cost Based Optimizations using Calcite framework."), - HIVE_CBO_RETPATH_HIVEOP("hive.cbo.returnpath.hiveop", false, "Flag to control calcite plan to hive operator conversion"), + HIVE_CBO_RETPATH_HIVEOP("hive.cbo.returnpath.hiveop", true, "Flag to control calcite plan to hive operator conversion"), HIVE_CBO_EXTENDED_COST_MODEL("hive.cbo.costmodel.extended", false, "Flag to control enabling the extended cost model based on" + "CPU, IO and cardinality. Otherwise, the cost model is based on cardinality."), HIVE_CBO_COST_MODEL_CPU("hive.cbo.costmodel.cpu", "0.000001", "Default cost of a comparison"), diff --git a/ql/src/test/results/clientpositive/alias_casted_column.q.out b/ql/src/test/results/clientpositive/alias_casted_column.q.out index 5b4ce82..1cbb56e 100644 --- a/ql/src/test/results/clientpositive/alias_casted_column.q.out +++ b/ql/src/test/results/clientpositive/alias_casted_column.q.out @@ -13,11 +13,11 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: t:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(key) (type: int) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -48,11 +48,11 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: t:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(key) (type: int) - outputColumnNames: _col0 + outputColumnNames: key2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/allcolref_in_udf.q.out b/ql/src/test/results/clientpositive/allcolref_in_udf.q.out index 216b037..1089a47 100644 --- a/ql/src/test/results/clientpositive/allcolref_in_udf.q.out +++ b/ql/src/test/results/clientpositive/allcolref_in_udf.q.out @@ -20,7 +20,7 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: concat(key, value) (type: string), array(key,value) (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _o__c0, _o__c1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -188,7 +188,7 @@ STAGE PLANS: alias: allcolref Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: c0 (type: array) + expressions: _o__c0 (type: array) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE UDTF Operator diff --git a/ql/src/test/results/clientpositive/alter_partition_change_col.q.out b/ql/src/test/results/clientpositive/alter_partition_change_col.q.out index 50520aa..d4ccbbc 100644 --- a/ql/src/test/results/clientpositive/alter_partition_change_col.q.out +++ b/ql/src/test/results/clientpositive/alter_partition_change_col.q.out @@ -41,10 +41,10 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@alter_partition_change_col0 POSTHOOK: Output: default@alter_partition_change_col1@p1=__HIVE_DEFAULT_PARTITION__/p2=123 POSTHOOK: Output: default@alter_partition_change_col1@p1=abc/p2=123 -POSTHOOK: Lineage: alter_partition_change_col1 PARTITION(p1=__HIVE_DEFAULT_PARTITION__,p2=123).c1 EXPRESSION [(alter_partition_change_col0)alter_partition_change_col0.FieldSchema(name:c1, type:string, comment:null), ] -POSTHOOK: Lineage: alter_partition_change_col1 PARTITION(p1=__HIVE_DEFAULT_PARTITION__,p2=123).c2 EXPRESSION [(alter_partition_change_col0)alter_partition_change_col0.FieldSchema(name:c2, type:string, comment:null), ] -POSTHOOK: Lineage: alter_partition_change_col1 PARTITION(p1=abc,p2=123).c1 EXPRESSION [(alter_partition_change_col0)alter_partition_change_col0.FieldSchema(name:c1, type:string, comment:null), ] -POSTHOOK: Lineage: alter_partition_change_col1 PARTITION(p1=abc,p2=123).c2 EXPRESSION [(alter_partition_change_col0)alter_partition_change_col0.FieldSchema(name:c2, type:string, comment:null), ] +POSTHOOK: Lineage: alter_partition_change_col1 PARTITION(p1=__HIVE_DEFAULT_PARTITION__,p2=123).c1 EXPRESSION [(alter_partition_change_col0)null-subquery1:_u1-subquery1:alter_partition_change_col0.FieldSchema(name:c1, type:string, comment:null), (alter_partition_change_col0)null-subquery2:_u1-subquery2:alter_partition_change_col0.FieldSchema(name:c1, type:string, comment:null), ] +POSTHOOK: Lineage: alter_partition_change_col1 PARTITION(p1=__HIVE_DEFAULT_PARTITION__,p2=123).c2 EXPRESSION [(alter_partition_change_col0)null-subquery1:_u1-subquery1:alter_partition_change_col0.FieldSchema(name:c2, type:string, comment:null), (alter_partition_change_col0)null-subquery2:_u1-subquery2:alter_partition_change_col0.FieldSchema(name:c2, type:string, comment:null), ] +POSTHOOK: Lineage: alter_partition_change_col1 PARTITION(p1=abc,p2=123).c1 EXPRESSION [(alter_partition_change_col0)null-subquery1:_u1-subquery1:alter_partition_change_col0.FieldSchema(name:c1, type:string, comment:null), (alter_partition_change_col0)null-subquery2:_u1-subquery2:alter_partition_change_col0.FieldSchema(name:c1, type:string, comment:null), ] +POSTHOOK: Lineage: alter_partition_change_col1 PARTITION(p1=abc,p2=123).c2 EXPRESSION [(alter_partition_change_col0)null-subquery1:_u1-subquery1:alter_partition_change_col0.FieldSchema(name:c2, type:string, comment:null), (alter_partition_change_col0)null-subquery2:_u1-subquery2:alter_partition_change_col0.FieldSchema(name:c2, type:string, comment:null), ] PREHOOK: query: show partitions alter_partition_change_col1 PREHOOK: type: SHOWPARTITIONS PREHOOK: Input: default@alter_partition_change_col1 diff --git a/ql/src/test/results/clientpositive/alter_partition_coltype.q.out b/ql/src/test/results/clientpositive/alter_partition_coltype.q.out index 9fc3c8d..039173d 100644 --- a/ql/src/test/results/clientpositive/alter_partition_coltype.q.out +++ b/ql/src/test/results/clientpositive/alter_partition_coltype.q.out @@ -232,36 +232,40 @@ STAGE PLANS: name: default.alter_coltype name: default.alter_coltype Truncated Path -> Alias: - /alter_coltype/dt=100/ts=3.0 [$hdt$_0:alter_coltype] - /alter_coltype/dt=100/ts=6.30 [$hdt$_0:alter_coltype] + /alter_coltype/dt=100/ts=3.0 [alter_coltype] + /alter_coltype/dt=100/ts=6.30 [alter_coltype] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns $f0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -411,35 +415,39 @@ STAGE PLANS: name: default.alter_coltype name: default.alter_coltype Truncated Path -> Alias: - /alter_coltype/dt=100/ts=6.30 [$hdt$_0:alter_coltype] + /alter_coltype/dt=100/ts=6.30 [alter_coltype] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns $f0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -568,35 +576,39 @@ STAGE PLANS: name: default.alter_coltype name: default.alter_coltype Truncated Path -> Alias: - /alter_coltype/dt=100/ts=3.0 [$hdt$_0:alter_coltype] + /alter_coltype/dt=100/ts=3.0 [alter_coltype] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns $f0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -806,7 +818,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string), dt (type: string), ts (type: double) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, dt, ts Statistics: Num rows: 50 Data size: 382 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1031,7 +1043,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: intcol (type: string) - outputColumnNames: _col0 + outputColumnNames: intcol Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1136,7 +1148,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: intcol (type: string) - outputColumnNames: _col0 + outputColumnNames: intcol Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/alter_table_cascade.q.out b/ql/src/test/results/clientpositive/alter_table_cascade.q.out index 3bf1a43..e541d8e 100644 --- a/ql/src/test/results/clientpositive/alter_table_cascade.q.out +++ b/ql/src/test/results/clientpositive/alter_table_cascade.q.out @@ -49,8 +49,8 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@alter_table_src POSTHOOK: Output: default@alter_table_cascade@p1=__HIVE_DEFAULT_PARTITION__/p2=123 POSTHOOK: Output: default@alter_table_cascade@p1=abc/p2=123 -POSTHOOK: Lineage: alter_table_cascade PARTITION(p1=__HIVE_DEFAULT_PARTITION__,p2=123).c1 EXPRESSION [(alter_table_src)alter_table_src.FieldSchema(name:c1, type:string, comment:null), ] -POSTHOOK: Lineage: alter_table_cascade PARTITION(p1=abc,p2=123).c1 EXPRESSION [(alter_table_src)alter_table_src.FieldSchema(name:c1, type:string, comment:null), ] +POSTHOOK: Lineage: alter_table_cascade PARTITION(p1=__HIVE_DEFAULT_PARTITION__,p2=123).c1 EXPRESSION [(alter_table_src)null-subquery1:_u1-subquery1:alter_table_src.FieldSchema(name:c1, type:string, comment:null), (alter_table_src)null-subquery2:_u1-subquery2:alter_table_src.FieldSchema(name:c1, type:string, comment:null), ] +POSTHOOK: Lineage: alter_table_cascade PARTITION(p1=abc,p2=123).c1 EXPRESSION [(alter_table_src)null-subquery1:_u1-subquery1:alter_table_src.FieldSchema(name:c1, type:string, comment:null), (alter_table_src)null-subquery2:_u1-subquery2:alter_table_src.FieldSchema(name:c1, type:string, comment:null), ] PREHOOK: query: show partitions alter_table_cascade PREHOOK: type: SHOWPARTITIONS PREHOOK: Input: default@alter_table_cascade @@ -914,8 +914,8 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@alter_table_src POSTHOOK: Output: default@alter_table_restrict@p1=__HIVE_DEFAULT_PARTITION__/p2=123 POSTHOOK: Output: default@alter_table_restrict@p1=abc/p2=123 -POSTHOOK: Lineage: alter_table_restrict PARTITION(p1=__HIVE_DEFAULT_PARTITION__,p2=123).c1 EXPRESSION [(alter_table_src)alter_table_src.FieldSchema(name:c1, type:string, comment:null), ] -POSTHOOK: Lineage: alter_table_restrict PARTITION(p1=abc,p2=123).c1 EXPRESSION [(alter_table_src)alter_table_src.FieldSchema(name:c1, type:string, comment:null), ] +POSTHOOK: Lineage: alter_table_restrict PARTITION(p1=__HIVE_DEFAULT_PARTITION__,p2=123).c1 EXPRESSION [(alter_table_src)null-subquery1:_u1-subquery1:alter_table_src.FieldSchema(name:c1, type:string, comment:null), (alter_table_src)null-subquery2:_u1-subquery2:alter_table_src.FieldSchema(name:c1, type:string, comment:null), ] +POSTHOOK: Lineage: alter_table_restrict PARTITION(p1=abc,p2=123).c1 EXPRESSION [(alter_table_src)null-subquery1:_u1-subquery1:alter_table_src.FieldSchema(name:c1, type:string, comment:null), (alter_table_src)null-subquery2:_u1-subquery2:alter_table_src.FieldSchema(name:c1, type:string, comment:null), ] PREHOOK: query: show partitions alter_table_restrict PREHOOK: type: SHOWPARTITIONS PREHOOK: Input: default@alter_table_restrict diff --git a/ql/src/test/results/clientpositive/ambiguitycheck.q.out b/ql/src/test/results/clientpositive/ambiguitycheck.q.out index c618cef..21051d2 100644 --- a/ql/src/test/results/clientpositive/ambiguitycheck.q.out +++ b/ql/src/test/results/clientpositive/ambiguitycheck.q.out @@ -743,7 +743,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: 1 (type: int) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 diff --git a/ql/src/test/results/clientpositive/analyze_table_null_partition.q.out b/ql/src/test/results/clientpositive/analyze_table_null_partition.q.out index c7254d1..eba9f5d 100644 --- a/ql/src/test/results/clientpositive/analyze_table_null_partition.q.out +++ b/ql/src/test/results/clientpositive/analyze_table_null_partition.q.out @@ -295,7 +295,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: name (type: string), age (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: name, age Statistics: Num rows: 5 Data size: 111 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/annotate_stats_deep_filters.q.out b/ql/src/test/results/clientpositive/annotate_stats_deep_filters.q.out index fc4f294..d2a5423 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_deep_filters.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_deep_filters.q.out @@ -123,7 +123,7 @@ STAGE PLANS: predicate: (((t = 1) and (si = 2)) or ((t = 2) and (si = 3)) or ((t = 3) and (si = 4)) or ((t = 4) and (si = 5)) or ((t = 5) and (si = 6)) or ((t = 6) and (si = 7)) or ((t = 7) and (si = 8)) or ((t = 9) and (si = 10)) or ((t = 10) and (si = 11)) or ((t = 11) and (si = 12)) or ((t = 12) and (si = 13)) or ((t = 13) and (si = 14)) or ((t = 14) and (si = 15)) or ((t = 15) and (si = 16)) or ((t = 16) and (si = 17)) or ((t = 17) and (si = 18)) or ((t = 27) and (si = 28)) or ((t = 37) and (si = 38)) or ((t = 47) and (si = 48)) or ((t = 52) and (si = 53))) (type: boolean) Statistics: Num rows: 280 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 280 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 280 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -137,15 +137,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -226,15 +230,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/annotate_stats_filter.q.out b/ql/src/test/results/clientpositive/annotate_stats_filter.q.out index 054b573..9cd0a58 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_filter.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_filter.q.out @@ -71,7 +71,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE ListSink @@ -99,7 +99,7 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 398 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'OH' (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 4 Data size: 398 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -147,7 +147,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'OH' (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -187,7 +187,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -223,7 +223,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -263,7 +263,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), null (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -301,7 +301,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), null (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -341,7 +341,7 @@ STAGE PLANS: Statistics: Num rows: 7 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 7 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -379,7 +379,7 @@ STAGE PLANS: Statistics: Num rows: 7 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 7 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -416,7 +416,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -442,7 +442,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -479,7 +479,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -540,7 +540,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -566,7 +566,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -604,7 +604,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -642,7 +642,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -682,7 +682,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -722,7 +722,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), null (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -760,7 +760,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'FL' (type: string), locid (type: int), zip (type: bigint), 2001 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -800,7 +800,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -840,7 +840,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'CA' (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -880,7 +880,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -916,7 +916,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -952,7 +952,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -988,7 +988,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/annotate_stats_groupby.q.out b/ql/src/test/results/clientpositive/annotate_stats_groupby.q.out index 82cc0da..35128b7 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_groupby.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_groupby.q.out @@ -111,7 +111,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE ListSink @@ -153,15 +153,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: loc_orc + alias: sq1:loc_orc Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: PARTIAL + outputColumnNames: state, locid + Statistics: Num rows: 8 Data size: 688 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: count() - keys: _col0 (type: string), _col1 (type: int) + keys: state (type: string), locid (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 8 Data size: 752 Basic stats: COMPLETE Column stats: PARTIAL @@ -176,15 +176,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: state, locid, $f2 Statistics: Num rows: 7 Data size: 658 Basic stats: COMPLETE Column stats: PARTIAL Select Operator - expressions: _col0 (type: string), _col2 (type: bigint), _col1 (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: state (type: string), $f2 (type: bigint), locid (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 7 Data size: 658 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator - aggregations: min(_col2) - keys: _col0 (type: string), _col1 (type: bigint) + aggregations: min($f2) + keys: $f0 (type: string), $f1 (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 7 Data size: 686 Basic stats: COMPLETE Column stats: PARTIAL @@ -210,15 +210,19 @@ STAGE PLANS: aggregations: min(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 7 Data size: 686 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), $f2 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 7 Data size: 686 Basic stats: COMPLETE Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 7 Data size: 686 Basic stats: COMPLETE Column stats: PARTIAL + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -255,10 +259,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: year (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: year + Statistics: Num rows: 8 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: int) + keys: year (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 8 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE @@ -271,15 +275,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: year Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: year (type: int) + outputColumnNames: year Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -308,10 +316,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: state, locid + Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: int) + keys: state (type: string), locid (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE @@ -324,15 +332,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: state (type: string), locid (type: int) + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -361,32 +373,35 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: state, locid + Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 32 Data size: 5600 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: int) Statistics: Num rows: 32 Data size: 5600 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 32 Data size: 5600 Basic stats: COMPLETE Column stats: COMPLETE - pruneGroupingSetId: true - File Output Operator - compressed: false - Statistics: Num rows: 32 Data size: 5600 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: state, locid + Statistics: Num rows: 32 Data size: 2880 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: state (type: string), locid (type: int) + outputColumnNames: state, locid + Statistics: Num rows: 32 Data size: 2880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 32 Data size: 2880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -415,32 +430,35 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: state, locid + Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 24 Data size: 4200 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: int) Statistics: Num rows: 24 Data size: 4200 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4200 Basic stats: COMPLETE Column stats: COMPLETE - pruneGroupingSetId: true - File Output Operator - compressed: false - Statistics: Num rows: 24 Data size: 4200 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: state, locid + Statistics: Num rows: 24 Data size: 2160 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: state (type: string), locid (type: int) + outputColumnNames: state, locid + Statistics: Num rows: 24 Data size: 2160 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 2160 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -469,32 +487,35 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: state, locid + Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 8 Data size: 1400 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: int) Statistics: Num rows: 8 Data size: 1400 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 1400 Basic stats: COMPLETE Column stats: COMPLETE - pruneGroupingSetId: true - File Output Operator - compressed: false - Statistics: Num rows: 8 Data size: 1400 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: state, locid + Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: state (type: string), locid (type: int) + outputColumnNames: state, locid + Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -523,32 +544,35 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: state, locid + Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: int) Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE - pruneGroupingSetId: true - File Output Operator - compressed: false - Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: state, locid + Statistics: Num rows: 16 Data size: 1440 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: state (type: string), locid (type: int) + outputColumnNames: state, locid + Statistics: Num rows: 16 Data size: 1440 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 16 Data size: 1440 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -577,32 +601,35 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: state, locid + Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 24 Data size: 4200 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: int) Statistics: Num rows: 24 Data size: 4200 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4200 Basic stats: COMPLETE Column stats: COMPLETE - pruneGroupingSetId: true - File Output Operator - compressed: false - Statistics: Num rows: 24 Data size: 4200 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: state, locid + Statistics: Num rows: 24 Data size: 2160 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: state (type: string), locid (type: int) + outputColumnNames: state, locid + Statistics: Num rows: 24 Data size: 2160 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 2160 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -631,32 +658,35 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: state, locid + Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 32 Data size: 5600 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: int) Statistics: Num rows: 32 Data size: 5600 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 32 Data size: 5600 Basic stats: COMPLETE Column stats: COMPLETE - pruneGroupingSetId: true - File Output Operator - compressed: false - Statistics: Num rows: 32 Data size: 5600 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: state, locid + Statistics: Num rows: 32 Data size: 2880 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: state (type: string), locid (type: int) + outputColumnNames: state, locid + Statistics: Num rows: 32 Data size: 2880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 32 Data size: 2880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -689,10 +719,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: year (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: year + Statistics: Num rows: 8 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: int) + keys: year (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE @@ -705,15 +735,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: year Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: year (type: int) + outputColumnNames: year Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -742,32 +776,35 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: state, locid + Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: int) Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE - pruneGroupingSetId: true - File Output Operator - compressed: false - Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: state, locid + Statistics: Num rows: 16 Data size: 1440 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: state (type: string), locid (type: int) + outputColumnNames: state, locid + Statistics: Num rows: 16 Data size: 1440 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 16 Data size: 1440 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -798,10 +835,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), zip (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: PARTIAL + outputColumnNames: state, zip + Statistics: Num rows: 8 Data size: 688 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator - keys: _col0 (type: string), _col1 (type: bigint) + keys: state (type: string), zip (type: bigint) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 4 Data size: 344 Basic stats: COMPLETE Column stats: PARTIAL @@ -814,15 +851,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: state, zip Statistics: Num rows: 4 Data size: 344 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false + Select Operator + expressions: state (type: string), zip (type: bigint) + outputColumnNames: state, zip Statistics: Num rows: 4 Data size: 344 Basic stats: COMPLETE Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 344 Basic stats: COMPLETE Column stats: PARTIAL + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -851,32 +892,35 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 32 Data size: 3184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: int) Statistics: Num rows: 32 Data size: 3184 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 16 Data size: 1592 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true - File Output Operator - compressed: false + Select Operator + expressions: state (type: string), locid (type: int) + outputColumnNames: state, locid Statistics: Num rows: 16 Data size: 1592 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 16 Data size: 1592 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -905,32 +949,35 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 24 Data size: 2388 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: int) Statistics: Num rows: 24 Data size: 2388 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 12 Data size: 1194 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true - File Output Operator - compressed: false + Select Operator + expressions: state (type: string), locid (type: int) + outputColumnNames: state, locid Statistics: Num rows: 12 Data size: 1194 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 1194 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -959,32 +1006,35 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: int) Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 4 Data size: 398 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true - File Output Operator - compressed: false + Select Operator + expressions: state (type: string), locid (type: int) + outputColumnNames: state, locid Statistics: Num rows: 4 Data size: 398 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 398 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1013,32 +1063,35 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 16 Data size: 1592 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: int) Statistics: Num rows: 16 Data size: 1592 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true - File Output Operator - compressed: false + Select Operator + expressions: state (type: string), locid (type: int) + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1067,32 +1120,35 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 24 Data size: 2388 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: int) Statistics: Num rows: 24 Data size: 2388 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 12 Data size: 1194 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true - File Output Operator - compressed: false + Select Operator + expressions: state (type: string), locid (type: int) + outputColumnNames: state, locid Statistics: Num rows: 12 Data size: 1194 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 1194 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1121,32 +1177,35 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 32 Data size: 3184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: int) Statistics: Num rows: 32 Data size: 3184 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 16 Data size: 1592 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true - File Output Operator - compressed: false + Select Operator + expressions: state (type: string), locid (type: int) + outputColumnNames: state, locid Statistics: Num rows: 16 Data size: 1592 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 16 Data size: 1592 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1175,10 +1234,10 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: year (type: int) - outputColumnNames: _col0 + outputColumnNames: year Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: year (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE @@ -1191,15 +1250,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: year Statistics: Num rows: 4 Data size: 398 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: year (type: int) + outputColumnNames: year Statistics: Num rows: 4 Data size: 398 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 398 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1228,32 +1291,35 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: int), '0' (type: string) + keys: state (type: string), locid (type: int), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 32 Data size: 3184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: int) Statistics: Num rows: 32 Data size: 3184 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 16 Data size: 1592 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true - File Output Operator - compressed: false + Select Operator + expressions: state (type: string), locid (type: int) + outputColumnNames: state, locid Statistics: Num rows: 16 Data size: 1592 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 16 Data size: 1592 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/annotate_stats_groupby2.q.out b/ql/src/test/results/clientpositive/annotate_stats_groupby2.q.out index 2cb1e84..3f507b9 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_groupby2.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_groupby2.q.out @@ -91,10 +91,10 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), country (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: state, country Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: state (type: string), country (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE @@ -107,15 +107,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: state, country Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: state (type: string), country (type: string) + outputColumnNames: state, country Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -144,32 +148,35 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), country (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: state, country Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + keys: state (type: string), country (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 80 Data size: 800 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 80 Data size: 800 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: state, country Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true - File Output Operator - compressed: false + Select Operator + expressions: state (type: string), country (type: string) + outputColumnNames: state, country Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -202,10 +209,10 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), country (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: state, country + Statistics: Num rows: 20 Data size: 3460 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: state (type: string), country (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 1384 Basic stats: COMPLETE Column stats: COMPLETE @@ -218,15 +225,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: state, country Statistics: Num rows: 2 Data size: 346 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: state (type: string), country (type: string) + outputColumnNames: state, country Statistics: Num rows: 2 Data size: 346 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 346 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -257,10 +268,10 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), votes (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: PARTIAL + outputColumnNames: state, votes + Statistics: Num rows: 20 Data size: 1720 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator - keys: _col0 (type: string), _col1 (type: bigint) + keys: state (type: string), votes (type: bigint) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 688 Basic stats: COMPLETE Column stats: PARTIAL @@ -273,15 +284,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: state, votes Statistics: Num rows: 2 Data size: 172 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false + Select Operator + expressions: state (type: string), votes (type: bigint) + outputColumnNames: state, votes Statistics: Num rows: 2 Data size: 172 Basic stats: COMPLETE Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 172 Basic stats: COMPLETE Column stats: PARTIAL + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -310,32 +325,35 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), country (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: state, country + Statistics: Num rows: 20 Data size: 3460 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + keys: state (type: string), country (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 32 Data size: 8256 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 32 Data size: 8256 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 2064 Basic stats: COMPLETE Column stats: COMPLETE - pruneGroupingSetId: true - File Output Operator - compressed: false - Statistics: Num rows: 8 Data size: 2064 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: state, country + Statistics: Num rows: 8 Data size: 1384 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: state (type: string), country (type: string) + outputColumnNames: state, country + Statistics: Num rows: 8 Data size: 1384 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 8 Data size: 1384 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -364,10 +382,10 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), country (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: state, country + Statistics: Num rows: 20 Data size: 3460 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: state (type: string), country (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 20 Data size: 3460 Basic stats: COMPLETE Column stats: COMPLETE @@ -380,15 +398,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: state, country Statistics: Num rows: 2 Data size: 346 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: state (type: string), country (type: string) + outputColumnNames: state, country Statistics: Num rows: 2 Data size: 346 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 346 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -417,32 +439,35 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), country (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: state, country + Statistics: Num rows: 20 Data size: 3460 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + keys: state (type: string), country (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 80 Data size: 20640 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 80 Data size: 20640 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 2064 Basic stats: COMPLETE Column stats: COMPLETE - pruneGroupingSetId: true - File Output Operator - compressed: false - Statistics: Num rows: 8 Data size: 2064 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: state, country + Statistics: Num rows: 8 Data size: 1384 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: state (type: string), country (type: string) + outputColumnNames: state, country + Statistics: Num rows: 8 Data size: 1384 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 8 Data size: 1384 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/annotate_stats_join.q.out b/ql/src/test/results/clientpositive/annotate_stats_join.q.out index bc44cc3..b1b4973 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_join.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_join.q.out @@ -170,14 +170,14 @@ STAGE PLANS: Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string), deptid (type: int), locid (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: lastname, deptid, locid Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: int) + key expressions: deptid (type: int) sort order: + - Map-reduce partition columns: _col1 (type: int) + Map-reduce partition columns: deptid (type: int) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col2 (type: int) + value expressions: lastname (type: string), locid (type: int) TableScan alias: d Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: COMPLETE @@ -186,30 +186,34 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: deptid (type: int), deptname (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: deptid, deptname Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: deptid (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: deptid (type: int) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) + value expressions: deptname (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + 0 deptid (type: int) + 1 deptid (type: int) + outputColumnNames: lastname, deptid, locid, deptid0, deptname Statistics: Num rows: 48 Data size: 9312 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: lastname (type: string), deptid (type: int), locid (type: int), deptid0 (type: int), deptname (type: string) + outputColumnNames: lastname, deptid, locid, deptid0, deptname Statistics: Num rows: 48 Data size: 9312 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 48 Data size: 9312 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -236,50 +240,48 @@ STAGE PLANS: TableScan alias: emp Statistics: Num rows: 48 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (deptid is not null and lastname is not null) (type: boolean) + Select Operator + expressions: lastname (type: string), deptid (type: int), locid (type: int) + outputColumnNames: lastname, deptid, locid Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: lastname (type: string), deptid (type: int), locid (type: int) - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: deptid (type: int), lastname (type: string) + sort order: ++ + Map-reduce partition columns: deptid (type: int), lastname (type: string) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: int), _col0 (type: string) - sort order: ++ - Map-reduce partition columns: _col1 (type: int), _col0 (type: string) - Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: int) + value expressions: locid (type: int) TableScan alias: dept Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (deptid is not null and deptname is not null) (type: boolean) + Select Operator + expressions: deptid (type: int), deptname (type: string) + outputColumnNames: deptid, deptname Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: deptid (type: int), deptname (type: string) - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: deptid (type: int), deptname (type: string) + sort order: ++ + Map-reduce partition columns: deptid (type: int), deptname (type: string) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int), _col0 (type: string) - 1 _col0 (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + 0 deptid (type: int), lastname (type: string) + 1 deptid (type: int), deptname (type: string) + outputColumnNames: lastname, deptid, locid, deptid0, deptname Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: lastname (type: string), deptid (type: int), locid (type: int), deptid0 (type: int), deptname (type: string) + outputColumnNames: lastname, deptid, locid, deptid0, deptname Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -303,18 +305,18 @@ STAGE PLANS: alias: e Statistics: Num rows: 48 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (deptid is not null and lastname is not null) (type: boolean) + predicate: (lastname is not null and deptid is not null) (type: boolean) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string), deptid (type: int), locid (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: lastname, deptid, locid Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: int), _col0 (type: string) + key expressions: deptid (type: int), lastname (type: string) sort order: ++ - Map-reduce partition columns: _col1 (type: int), _col0 (type: string) + Map-reduce partition columns: deptid (type: int), lastname (type: string) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: int) + value expressions: locid (type: int) TableScan alias: d Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: COMPLETE @@ -323,29 +325,33 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: deptid (type: int), deptname (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: deptid, deptname Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) + key expressions: deptid (type: int), deptname (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Map-reduce partition columns: deptid (type: int), deptname (type: string) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int), _col0 (type: string) - 1 _col0 (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + 0 deptid (type: int), lastname (type: string) + 1 deptid (type: int), deptname (type: string) + outputColumnNames: lastname, deptid, locid, deptid0, deptname Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: lastname (type: string), deptid (type: int), locid (type: int), deptid0 (type: int), deptname (type: string) + outputColumnNames: lastname, deptid, locid, deptid0, deptname Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -372,50 +378,48 @@ STAGE PLANS: TableScan alias: emp Statistics: Num rows: 48 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (deptid is not null and lastname is not null) (type: boolean) + Select Operator + expressions: lastname (type: string), deptid (type: int), locid (type: int) + outputColumnNames: lastname, deptid, locid Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: lastname (type: string), deptid (type: int), locid (type: int) - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: deptid (type: int), lastname (type: string) + sort order: ++ + Map-reduce partition columns: deptid (type: int), lastname (type: string) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: int), _col0 (type: string), _col0 (type: string) - sort order: +++ - Map-reduce partition columns: _col1 (type: int), _col0 (type: string), _col0 (type: string) - Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: int) + value expressions: locid (type: int) TableScan alias: dept Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (deptid is not null and deptname is not null) (type: boolean) + Select Operator + expressions: deptid (type: int), deptname (type: string) + outputColumnNames: deptid, deptname Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: deptid (type: int), deptname (type: string) - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: deptid (type: int), deptname (type: string) + sort order: ++ + Map-reduce partition columns: deptid (type: int), deptname (type: string) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string), _col1 (type: string) - sort order: +++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col1 (type: string) - Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int), _col0 (type: string), _col0 (type: string) - 1 _col0 (type: int), _col1 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 11 Data size: 2134 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 11 Data size: 2134 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 deptid (type: int), lastname (type: string) + 1 deptid (type: int), deptname (type: string) + outputColumnNames: lastname, deptid, locid, deptid0, deptname + Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: lastname (type: string), deptid (type: int), locid (type: int), deptid0 (type: int), deptname (type: string) + outputColumnNames: lastname, deptid, locid, deptid0, deptname + Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -447,14 +451,14 @@ STAGE PLANS: Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string), deptid (type: int), locid (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: lastname, deptid, locid Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: int) + key expressions: deptid (type: int) sort order: + - Map-reduce partition columns: _col1 (type: int) + Map-reduce partition columns: deptid (type: int) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col2 (type: int) + value expressions: lastname (type: string), locid (type: int) TableScan alias: d Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: COMPLETE @@ -463,48 +467,52 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: deptid (type: int), deptname (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: deptid, deptname Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: deptid (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: deptid (type: int) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) + value expressions: deptname (type: string) TableScan - alias: e + alias: e1 Statistics: Num rows: 48 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: deptid is not null (type: boolean) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string), deptid (type: int), locid (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: lastname, deptid, locid Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: int) + key expressions: deptid (type: int) sort order: + - Map-reduce partition columns: _col1 (type: int) + Map-reduce partition columns: deptid (type: int) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col2 (type: int) + value expressions: lastname (type: string), locid (type: int) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - 2 _col1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + 0 deptid (type: int) + 1 deptid (type: int) + 2 deptid (type: int) + outputColumnNames: lastname, deptid, locid, deptid0, deptname, lastname0, deptid1, locid0 Statistics: Num rows: 768 Data size: 225024 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: lastname (type: string), deptid (type: int), locid (type: int), deptid0 (type: int), deptname (type: string), lastname0 (type: string), deptid1 (type: int), locid0 (type: int) + outputColumnNames: lastname, deptid, locid, deptid0, deptname, lastname0, deptid1, locid0 Statistics: Num rows: 768 Data size: 225024 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 768 Data size: 225024 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -534,30 +542,14 @@ STAGE PLANS: Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string), deptid (type: int), locid (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: lastname, deptid, locid Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: int) + key expressions: deptid (type: int) sort order: + - Map-reduce partition columns: _col1 (type: int) + Map-reduce partition columns: deptid (type: int) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col2 (type: int) - TableScan - alias: d - Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: deptid is not null (type: boolean) - Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: deptid (type: int), deptname (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) + value expressions: lastname (type: string), locid (type: int) TableScan alias: l Statistics: Num rows: 8 Data size: 109 Basic stats: COMPLETE Column stats: COMPLETE @@ -566,32 +558,52 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: int) + key expressions: locid (type: int) sort order: + - Map-reduce partition columns: _col1 (type: int) + Map-reduce partition columns: locid (type: int) Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col2 (type: bigint), _col3 (type: int) + value expressions: state (type: string), zip (type: bigint), year (type: int) + TableScan + alias: d + Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: deptid is not null (type: boolean) + Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: deptid (type: int), deptname (type: string) + outputColumnNames: deptid, deptname + Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: deptid (type: int) + sort order: + + Map-reduce partition columns: deptid (type: int) + Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: deptname (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - 2 _col1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + 0 deptid (type: int) + 1 locid (type: int) + 2 deptid (type: int) + outputColumnNames: lastname, deptid, locid, state, locid0, zip, year, deptid0, deptname Statistics: Num rows: 47 Data size: 13912 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: lastname (type: string), deptid (type: int), locid (type: int), deptid0 (type: int), deptname (type: string), state (type: string), locid0 (type: int), zip (type: bigint), year (type: int) + outputColumnNames: lastname, deptid, locid, deptid0, deptname, state, locid0, zip, year Statistics: Num rows: 47 Data size: 13912 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 47 Data size: 13912 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -623,14 +635,14 @@ STAGE PLANS: Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string), deptid (type: int), locid (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: lastname, deptid, locid Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: int), _col0 (type: string) + key expressions: deptid (type: int), lastname (type: string) sort order: ++ - Map-reduce partition columns: _col1 (type: int), _col0 (type: string) + Map-reduce partition columns: deptid (type: int), lastname (type: string) Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: int) + value expressions: locid (type: int) TableScan alias: d Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: COMPLETE @@ -639,47 +651,51 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: deptid (type: int), deptname (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: deptid, deptname Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) + key expressions: deptid (type: int), deptname (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Map-reduce partition columns: deptid (type: int), deptname (type: string) Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: l Statistics: Num rows: 8 Data size: 109 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (locid is not null and state is not null) (type: boolean) + predicate: (state is not null and locid is not null) (type: boolean) Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: int), _col0 (type: string) + key expressions: locid (type: int), state (type: string) sort order: ++ - Map-reduce partition columns: _col1 (type: int), _col0 (type: string) + Map-reduce partition columns: locid (type: int), state (type: string) Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: bigint), _col3 (type: int) + value expressions: zip (type: bigint), year (type: int) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 _col1 (type: int), _col0 (type: string) - 1 _col0 (type: int), _col1 (type: string) - 2 _col1 (type: int), _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + 0 deptid (type: int), lastname (type: string) + 1 deptid (type: int), deptname (type: string) + 2 locid (type: int), state (type: string) + outputColumnNames: lastname, deptid, locid, deptid0, deptname, state, locid0, zip, year Statistics: Num rows: 1 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: lastname (type: string), deptid (type: int), locid (type: int), deptid0 (type: int), deptname (type: string), state (type: string), locid0 (type: int), zip (type: bigint), year (type: int) + outputColumnNames: lastname, deptid, locid, deptid0, deptname, state, locid0, zip, year Statistics: Num rows: 1 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out b/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out index c864c04..5b7d84e 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out @@ -280,12 +280,12 @@ STAGE PLANS: Statistics: Num rows: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: ss_store_sk Statistics: Num rows: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: ss_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: ss_store_sk (type: int) Statistics: Num rows: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: s @@ -295,25 +295,25 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: s_store_sk Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: s_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: s_store_sk (type: int) Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 + 0 ss_store_sk (type: int) + 1 s_store_sk (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 964 Data size: 3856 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col1 (type: int) - outputColumnNames: _col0 + expressions: s_store_sk (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 964 Data size: 3856 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -349,12 +349,12 @@ STAGE PLANS: Statistics: Num rows: 333 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: ss_store_sk Statistics: Num rows: 333 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: ss_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: ss_store_sk (type: int) Statistics: Num rows: 333 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: s @@ -364,25 +364,25 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: s_store_sk Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: s_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: s_store_sk (type: int) Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 + 0 ss_store_sk (type: int) + 1 s_store_sk (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 136 Data size: 544 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col1 (type: int) - outputColumnNames: _col0 + expressions: s_store_sk (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 136 Data size: 544 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -414,44 +414,44 @@ STAGE PLANS: alias: ss Statistics: Num rows: 1000 Data size: 130523 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ss_quantity > 10) and ss_store_sk is not null) (type: boolean) + predicate: (ss_store_sk is not null and (ss_quantity > 10)) (type: boolean) Statistics: Num rows: 321 Data size: 2460 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: ss_store_sk Statistics: Num rows: 321 Data size: 2460 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: ss_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: ss_store_sk (type: int) Statistics: Num rows: 321 Data size: 2460 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: s Statistics: Num rows: 12 Data size: 3143 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator - predicate: ((s_company_id > 0) and s_store_sk is not null) (type: boolean) + predicate: (s_store_sk is not null and (s_company_id > 0)) (type: boolean) Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: s_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: s_store_sk Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: s_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: s_store_sk (type: int) Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2 + 0 ss_store_sk (type: int) + 1 s_store_sk (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 131 Data size: 524 Basic stats: COMPLETE Column stats: PARTIAL Select Operator - expressions: _col2 (type: int) - outputColumnNames: _col0 + expressions: s_store_sk (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 131 Data size: 524 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false @@ -487,40 +487,40 @@ STAGE PLANS: Statistics: Num rows: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: ss_store_sk Statistics: Num rows: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: ss_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: ss_store_sk (type: int) Statistics: Num rows: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: s Statistics: Num rows: 12 Data size: 3143 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((s_floor_space > 0) and s_store_sk is not null) (type: boolean) + predicate: (s_store_sk is not null and (s_floor_space > 0)) (type: boolean) Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: s_store_sk Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: s_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: s_store_sk (type: int) Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 + 0 ss_store_sk (type: int) + 1 s_store_sk (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 393 Data size: 1572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col1 (type: int) - outputColumnNames: _col0 + expressions: s_store_sk (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 393 Data size: 1572 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -552,16 +552,16 @@ STAGE PLANS: alias: ss Statistics: Num rows: 1000 Data size: 130523 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ss_quantity > 10) and ss_store_sk is not null) (type: boolean) + predicate: (ss_store_sk is not null and (ss_quantity > 10)) (type: boolean) Statistics: Num rows: 321 Data size: 2460 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: ss_store_sk Statistics: Num rows: 321 Data size: 2460 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: ss_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: ss_store_sk (type: int) Statistics: Num rows: 321 Data size: 2460 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: s @@ -571,25 +571,25 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: s_store_sk Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: s_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: s_store_sk (type: int) Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2 + 0 ss_store_sk (type: int) + 1 s_store_sk (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col2 (type: int) - outputColumnNames: _col0 + expressions: s_store_sk (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -625,12 +625,12 @@ STAGE PLANS: Statistics: Num rows: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: ss_store_sk Statistics: Num rows: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: ss_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: ss_store_sk (type: int) Statistics: Num rows: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: s @@ -640,27 +640,27 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: s_store_sk Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: s_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: s_store_sk (type: int) Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE TableScan - alias: s + alias: s1 Statistics: Num rows: 12 Data size: 3143 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s_store_sk is not null (type: boolean) Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: s_store_sk Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: s_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: s_store_sk (type: int) Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator @@ -668,14 +668,14 @@ STAGE PLANS: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col1 + 0 ss_store_sk (type: int) + 1 s_store_sk (type: int) + 2 s_store_sk (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 821 Data size: 3284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col1 (type: int) - outputColumnNames: _col0 + expressions: s_store_sk (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 821 Data size: 3284 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -711,12 +711,12 @@ STAGE PLANS: Statistics: Num rows: 333 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: ss_store_sk Statistics: Num rows: 333 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: ss_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: ss_store_sk (type: int) Statistics: Num rows: 333 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: s @@ -726,27 +726,27 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: s_store_sk Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: s_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: s_store_sk (type: int) Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE TableScan - alias: s + alias: s1 Statistics: Num rows: 12 Data size: 3143 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (s_store_sk > 1000) (type: boolean) Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: s_store_sk Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: s_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: s_store_sk (type: int) Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator @@ -754,14 +754,14 @@ STAGE PLANS: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col1 + 0 ss_store_sk (type: int) + 1 s_store_sk (type: int) + 2 s_store_sk (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 213 Data size: 852 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col1 (type: int) - outputColumnNames: _col0 + expressions: s_store_sk (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 213 Data size: 852 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -797,57 +797,57 @@ STAGE PLANS: Statistics: Num rows: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: ss_store_sk Statistics: Num rows: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: ss_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: ss_store_sk (type: int) Statistics: Num rows: 964 Data size: 3716 Basic stats: COMPLETE Column stats: COMPLETE TableScan - alias: s + alias: s1 Statistics: Num rows: 12 Data size: 3143 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((s_floor_space > 1000) and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + predicate: s_store_sk is not null (type: boolean) + Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: s_store_sk + Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: s_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: s_store_sk (type: int) + Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: s Statistics: Num rows: 12 Data size: 3143 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (s_store_sk is not null and (s_floor_space > 1000)) (type: boolean) + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: s_store_sk + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: s_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: s_store_sk (type: int) + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col1 + 0 ss_store_sk (type: int) + 1 s_store_sk (type: int) + 2 s_store_sk (type: int) + outputColumnNames: s_store_sk0 Statistics: Num rows: 508 Data size: 2032 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col1 (type: int) - outputColumnNames: _col0 + expressions: s_store_sk0 (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 508 Data size: 2032 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -879,16 +879,16 @@ STAGE PLANS: alias: ss Statistics: Num rows: 1000 Data size: 130523 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ss_quantity > 10) and ss_store_sk is not null) (type: boolean) + predicate: (ss_store_sk is not null and (ss_quantity > 10)) (type: boolean) Statistics: Num rows: 321 Data size: 2460 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: ss_store_sk Statistics: Num rows: 321 Data size: 2460 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: ss_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: ss_store_sk (type: int) Statistics: Num rows: 321 Data size: 2460 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: s @@ -898,27 +898,27 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: s_store_sk Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: s_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: s_store_sk (type: int) Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE TableScan - alias: s + alias: s1 Statistics: Num rows: 12 Data size: 3143 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s_store_sk is not null (type: boolean) Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) - outputColumnNames: _col0 + outputColumnNames: s_store_sk Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: s_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: s_store_sk (type: int) Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator @@ -926,14 +926,14 @@ STAGE PLANS: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col2 + 0 ss_store_sk (type: int) + 1 s_store_sk (type: int) + 2 s_store_sk (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 273 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col2 (type: int) - outputColumnNames: _col0 + expressions: s_store_sk (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 273 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -954,97 +954,101 @@ PREHOOK: type: QUERY POSTHOOK: query: explain select s.s_store_sk from store s join store_sales ss on (s.s_store_sk = ss.ss_store_sk) join customer_address ca on (ca.ca_address_sk = ss.ss_addr_sk) POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan alias: ss Statistics: Num rows: 1000 Data size: 130523 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_addr_sk is not null and ss_store_sk is not null) (type: boolean) + predicate: (ss_store_sk is not null and ss_addr_sk is not null) (type: boolean) Statistics: Num rows: 916 Data size: 7012 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_addr_sk (type: int), ss_store_sk (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: ss_addr_sk, ss_store_sk Statistics: Num rows: 916 Data size: 7012 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: ss_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: ss_store_sk (type: int) Statistics: Num rows: 916 Data size: 7012 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: int) + value expressions: ss_addr_sk (type: int) TableScan - alias: ca - Statistics: Num rows: 20 Data size: 2114 Basic stats: COMPLETE Column stats: COMPLETE + alias: s + Statistics: Num rows: 12 Data size: 3143 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + predicate: s_store_sk is not null (type: boolean) + Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ca_address_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + expressions: s_store_sk (type: int) + outputColumnNames: s_store_sk + Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: s_store_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: s_store_sk (type: int) + Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 210 Data size: 840 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 0 ss_store_sk (type: int) + 1 s_store_sk (type: int) + outputColumnNames: ss_addr_sk, s_store_sk + Statistics: Num rows: 916 Data size: 7328 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ss_addr_sk is not null (type: boolean) + Statistics: Num rows: 916 Data size: 7328 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 210 Data size: 840 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: s - Statistics: Num rows: 12 Data size: 3143 Basic stats: COMPLETE Column stats: COMPLETE + alias: ca + Statistics: Num rows: 20 Data size: 2114 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + predicate: ca_address_sk is not null (type: boolean) + Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: s_store_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + expressions: ca_address_sk (type: int) + outputColumnNames: ca_address_sk + Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: ca_address_sk (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: ca_address_sk (type: int) + Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + TableScan + Reduce Output Operator + key expressions: ss_addr_sk (type: int) + sort order: + + Map-reduce partition columns: ss_addr_sk (type: int) + Statistics: Num rows: 916 Data size: 7328 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: s_store_sk (type: int) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col3 + 0 ca_address_sk (type: int) + 1 ss_addr_sk (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 210 Data size: 840 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col3 (type: int) - outputColumnNames: _col0 + expressions: s_store_sk (type: int) + outputColumnNames: s_store_sk Statistics: Num rows: 210 Data size: 840 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/annotate_stats_limit.q.out b/ql/src/test/results/clientpositive/annotate_stats_limit.q.out index 7300ea0..28a9b74 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_limit.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_limit.q.out @@ -79,7 +79,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -102,7 +102,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 4 @@ -130,7 +130,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 16 @@ -156,7 +156,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 0 diff --git a/ql/src/test/results/clientpositive/annotate_stats_part.q.out b/ql/src/test/results/clientpositive/annotate_stats_part.q.out index 2bec917..e726f63 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_part.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_part.q.out @@ -59,7 +59,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: PARTIAL ListSink @@ -98,10 +98,10 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 6 Data size: 767 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 780 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: PARTIAL ListSink @@ -133,11 +133,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 3 Data size: 342 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), '__HIVE_DEFAULT_PARTITION__' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 342 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: state, locid, zip, year + Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: -- basicStatState: PARTIAL colStatState: NONE @@ -159,7 +159,7 @@ STAGE PLANS: Statistics: Num rows: 7 Data size: 678 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 7 Data size: 678 Basic stats: PARTIAL Column stats: PARTIAL ListSink @@ -182,7 +182,7 @@ STAGE PLANS: Statistics: Num rows: 7 Data size: 678 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), '2001' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 7 Data size: 678 Basic stats: COMPLETE Column stats: NONE ListSink @@ -219,7 +219,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), '__HIVE_DEFAULT_PARTITION__' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE ListSink @@ -242,7 +242,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 774 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 1472 Basic stats: COMPLETE Column stats: PARTIAL ListSink @@ -265,7 +265,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 774 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 1472 Basic stats: COMPLETE Column stats: PARTIAL ListSink @@ -293,7 +293,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), '__HIVE_DEFAULT_PARTITION__' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: PARTIAL ListSink @@ -328,7 +328,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 774 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: zip (type: bigint) - outputColumnNames: _col0 + outputColumnNames: zip Statistics: Num rows: 8 Data size: 774 Basic stats: COMPLETE Column stats: NONE ListSink @@ -351,7 +351,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 774 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string) - outputColumnNames: _col0 + outputColumnNames: state Statistics: Num rows: 8 Data size: 688 Basic stats: COMPLETE Column stats: PARTIAL ListSink @@ -374,7 +374,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: year (type: string) - outputColumnNames: _col0 + outputColumnNames: year Statistics: Num rows: 8 Data size: 1472 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -399,7 +399,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 774 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 8 Data size: 720 Basic stats: COMPLETE Column stats: PARTIAL ListSink @@ -422,7 +422,7 @@ STAGE PLANS: Statistics: Num rows: 7 Data size: 678 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 7 Data size: 630 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -445,7 +445,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE ListSink @@ -468,7 +468,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 774 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 2192 Basic stats: COMPLETE Column stats: PARTIAL ListSink @@ -496,7 +496,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: locid (type: int) - outputColumnNames: _col0 + outputColumnNames: locid Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -520,7 +520,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: locid (type: int), '2001' (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: locid, year Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -537,14 +537,14 @@ STAGE PLANS: limit: -1 Processor Tree: TableScan - alias: loc_orc + alias: test:loc_orc Statistics: Num rows: 7 Data size: 678 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (locid > 0) (type: boolean) Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: locid (type: int), '2001' (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: locid, year Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE ListSink diff --git a/ql/src/test/results/clientpositive/annotate_stats_select.q.out b/ql/src/test/results/clientpositive/annotate_stats_select.q.out index 877037d..fd610f9 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_select.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_select.q.out @@ -108,7 +108,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: bo1 (type: boolean), ti1 (type: tinyint), si1 (type: smallint), i1 (type: int), bi1 (type: bigint), f1 (type: float), d1 (type: double), de1 (type: decimal(10,0)), ts1 (type: timestamp), da1 (type: timestamp), s1 (type: string), vc1 (type: varchar(5)), m1 (type: map), l1 (type: array), st1 (type: struct) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + outputColumnNames: bo1, ti1, si1, i1, bi1, f1, d1, de1, ts1, da1, s1, vc1, m1, l1, st1 Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: NONE ListSink @@ -141,7 +141,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: bo1 (type: boolean), ti1 (type: tinyint), si1 (type: smallint), i1 (type: int), bi1 (type: bigint), f1 (type: float), d1 (type: double), de1 (type: decimal(10,0)), ts1 (type: timestamp), da1 (type: timestamp), s1 (type: string), vc1 (type: varchar(5)), m1 (type: map), l1 (type: array), st1 (type: struct) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + outputColumnNames: bo1, ti1, si1, i1, bi1, f1, d1, de1, ts1, da1, s1, vc1, m1, l1, st1 Statistics: Num rows: 2 Data size: 420 Basic stats: COMPLETE Column stats: PARTIAL ListSink @@ -164,7 +164,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: bo1 (type: boolean) - outputColumnNames: _col0 + outputColumnNames: bo1 Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -189,7 +189,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i1 (type: int) - outputColumnNames: _col0 + outputColumnNames: i1 Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -212,7 +212,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s1 (type: string) - outputColumnNames: _col0 + outputColumnNames: s1 Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -237,7 +237,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: m1 (type: map) - outputColumnNames: _col0 + outputColumnNames: m1 Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: NONE ListSink @@ -260,7 +260,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: bo1 (type: boolean), ti1 (type: tinyint), si1 (type: smallint), i1 (type: int), bi1 (type: bigint), f1 (type: float), d1 (type: double), s1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + outputColumnNames: bo1, ti1, si1, i1, bi1, f1, d1, s1 Statistics: Num rows: 2 Data size: 246 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -283,7 +283,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: null (type: void) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE ListSink @@ -306,7 +306,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 11 (type: int) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -329,7 +329,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 11 (type: bigint) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -352,7 +352,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 11.0 (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -375,7 +375,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'hello' (type: string) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -395,8 +395,8 @@ STAGE PLANS: alias: alltypes_orc Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'hello' (type: char(5)) - outputColumnNames: _col0 + expressions: 'hello' (type: string) + outputColumnNames: _o__c0 Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -417,7 +417,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'hello' (type: varchar(5)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -440,7 +440,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: D317B6 (type: binary) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 2 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -463,7 +463,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1 (type: tinyint), 20 (type: smallint) - outputColumnNames: _col0, _col1 + outputColumnNames: _o__c0, _o__c1 Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -486,7 +486,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1970-12-31 15:59:58.174 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -509,7 +509,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: null (type: date) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE ListSink @@ -532,7 +532,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 58 (type: decimal(10,0)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -555,7 +555,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: array(1,2,3) (type: array) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -590,7 +590,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: str_to_map('a=1 b=2 c=3',' ','=') (type: map) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 2 Data size: 1508 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -625,7 +625,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: named_struct('a',11,'b',11) (type: struct) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -696,7 +696,7 @@ STAGE PLANS: alias: alltypes_orc Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -710,15 +710,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -746,9 +750,11 @@ STAGE PLANS: alias: alltypes_orc Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -760,15 +766,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -797,7 +807,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: bo1 (type: boolean), ti1 (type: tinyint), si1 (type: smallint), i1 (type: int), bi1 (type: bigint), f1 (type: float), d1 (type: double), de1 (type: decimal(10,0)), ts1 (type: timestamp), da1 (type: timestamp), s1 (type: string), vc1 (type: varchar(5)), m1 (type: map), l1 (type: array), st1 (type: struct), 11 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 + outputColumnNames: bo1, ti1, si1, i1, bi1, f1, d1, de1, ts1, da1, s1, vc1, m1, l1, st1, _o__c1 Statistics: Num rows: 2 Data size: 428 Basic stats: COMPLETE Column stats: PARTIAL ListSink @@ -820,11 +830,11 @@ STAGE PLANS: limit: 10 Processor Tree: TableScan - alias: alltypes_orc + alias: temp:alltypes_orc Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i1 (type: int) - outputColumnNames: _col0 + outputColumnNames: i1 Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 @@ -848,11 +858,11 @@ STAGE PLANS: limit: 10 Processor Tree: TableScan - alias: alltypes_orc + alias: temp:alltypes_orc Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i1 (type: int) - outputColumnNames: _col0 + outputColumnNames: i1 Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 @@ -868,52 +878,28 @@ POSTHOOK: query: -- inner select - numRows: 2 rawDataSize: 16 explain select i1,"hello" from (select i1,11 from alltypes_orc limit 10) temp POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypes_orc - Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: i1 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), 'hello' (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-0 Fetch Operator - limit: -1 + limit: 10 Processor Tree: - ListSink + TableScan + alias: temp:alltypes_orc + Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i1 (type: int) + outputColumnNames: i1 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 10 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i1 (type: int), 'hello' (type: string) + outputColumnNames: i1, _o__c1 + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE + ListSink PREHOOK: query: -- inner select - numRows: 2 rawDataSize: 24 -- outer select - numRows: 2 rawDataSize: 16 @@ -932,11 +918,11 @@ STAGE PLANS: limit: 10 Processor Tree: TableScan - alias: alltypes_orc + alias: temp:alltypes_orc Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 11.0 (type: double) - outputColumnNames: _col0 + outputColumnNames: x Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 @@ -952,52 +938,28 @@ POSTHOOK: query: -- inner select - numRows: 2 rawDataSize: 104 explain select x,"hello" from (select i1 as x, unbase64("0xe23") as ub from alltypes_orc limit 10) temp POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypes_orc - Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: i1 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), 'hello' (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-0 Fetch Operator - limit: -1 + limit: 10 Processor Tree: - ListSink + TableScan + alias: temp:alltypes_orc + Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i1 (type: int) + outputColumnNames: i1 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 10 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i1 (type: int), 'hello' (type: string) + outputColumnNames: x, _o__c1 + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE + ListSink PREHOOK: query: -- inner select - numRows: 2 rawDataSize: 186 -- middle select - numRows: 2 rawDataSize: 178 @@ -1010,67 +972,31 @@ POSTHOOK: query: -- inner select - numRows: 2 rawDataSize: 186 explain select h, 11.0 from (select hell as h from (select i1, "hello" as hell from alltypes_orc limit 10) in1 limit 10) in2 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypes_orc - Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator + Stage: Stage-0 + Fetch Operator + limit: 10 + Processor Tree: + TableScan + alias: in2:in1:alltypes_orc + Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 'hello' (type: string) + outputColumnNames: hell + Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 10 Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Limit - Number of rows: 10 - Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Limit - Number of rows: 10 - Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 'hello' (type: string), 11.0 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink + Select Operator + expressions: hell (type: char(5)), 11.0 (type: double) + outputColumnNames: h, _o__c1 + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE + ListSink PREHOOK: query: -- This test is for FILTER operator where filter expression is a boolean column -- numRows: 2 rawDataSize: 8 @@ -1096,7 +1022,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: bo1 (type: boolean) - outputColumnNames: _col0 + outputColumnNames: bo1 Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -1134,7 +1060,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: bo1 (type: boolean) - outputColumnNames: _col0 + outputColumnNames: bo1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/annotate_stats_table.q.out b/ql/src/test/results/clientpositive/annotate_stats_table.q.out index 87e2fa6..f01156b 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_table.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_table.q.out @@ -47,7 +47,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: lastname (type: string), deptid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: lastname, deptid Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE ListSink @@ -89,11 +89,11 @@ STAGE PLANS: Processor Tree: TableScan alias: emp_orc - Statistics: Num rows: 3 Data size: 384 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 394 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: lastname (type: string), deptid (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 384 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: lastname, deptid + Statistics: Num rows: 3 Data size: 394 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: -- table level analyze statistics @@ -125,7 +125,7 @@ STAGE PLANS: Statistics: Num rows: 48 Data size: 4512 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: lastname (type: string), deptid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: lastname, deptid Statistics: Num rows: 48 Data size: 4512 Basic stats: COMPLETE Column stats: NONE ListSink @@ -158,7 +158,7 @@ STAGE PLANS: Statistics: Num rows: 48 Data size: 4512 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: lastname (type: string), deptid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: lastname, deptid Statistics: Num rows: 48 Data size: 192 Basic stats: COMPLETE Column stats: PARTIAL ListSink @@ -183,7 +183,7 @@ STAGE PLANS: Statistics: Num rows: 48 Data size: 4512 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: deptid (type: int) - outputColumnNames: _col0 + outputColumnNames: deptid Statistics: Num rows: 48 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -216,7 +216,7 @@ STAGE PLANS: Statistics: Num rows: 48 Data size: 4512 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string), deptid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: lastname, deptid Statistics: Num rows: 48 Data size: 4560 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -239,7 +239,7 @@ STAGE PLANS: Statistics: Num rows: 48 Data size: 4512 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string) - outputColumnNames: _col0 + outputColumnNames: lastname Statistics: Num rows: 48 Data size: 4368 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -262,7 +262,7 @@ STAGE PLANS: Statistics: Num rows: 48 Data size: 4512 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: deptid (type: int) - outputColumnNames: _col0 + outputColumnNames: deptid Statistics: Num rows: 48 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -285,7 +285,7 @@ STAGE PLANS: Statistics: Num rows: 48 Data size: 4512 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string), deptid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: lastname, deptid Statistics: Num rows: 48 Data size: 4560 Basic stats: COMPLETE Column stats: COMPLETE ListSink diff --git a/ql/src/test/results/clientpositive/annotate_stats_union.q.out b/ql/src/test/results/clientpositive/annotate_stats_union.q.out index e09dde3..d157282 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_union.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_union.q.out @@ -79,7 +79,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string) - outputColumnNames: _col0 + outputColumnNames: state Statistics: Num rows: 8 Data size: 688 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -98,37 +98,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: loc_orc + alias: null-subquery1:tmp-subquery1:loc_orc Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string) - outputColumnNames: _col0 + outputColumnNames: state Statistics: Num rows: 8 Data size: 688 Basic stats: COMPLETE Column stats: COMPLETE Union Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: state (type: string) + outputColumnNames: state Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: loc_orc + alias: null-subquery2:tmp-subquery2:loc_orc Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string) - outputColumnNames: _col0 + outputColumnNames: state Statistics: Num rows: 8 Data size: 688 Basic stats: COMPLETE Column stats: COMPLETE Union Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: state (type: string) + outputColumnNames: state Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -155,7 +163,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -174,37 +182,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: loc_orc + alias: null-subquery1:tmp-subquery1:loc_orc Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Union Statistics: Num rows: 16 Data size: 1608 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) + outputColumnNames: state, locid, zip, year Statistics: Num rows: 16 Data size: 1608 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 16 Data size: 1608 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: loc_orc + alias: null-subquery2:tmp-subquery2:loc_orc Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, zip, year Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE Union Statistics: Num rows: 16 Data size: 1608 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) + outputColumnNames: state, locid, zip, year Statistics: Num rows: 16 Data size: 1608 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 16 Data size: 1608 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -317,37 +333,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: loc_orc + alias: null-subquery1:temp-subquery1:loc_orc Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string) - outputColumnNames: _col0 + outputColumnNames: state Statistics: Num rows: 8 Data size: 688 Basic stats: COMPLETE Column stats: COMPLETE Union Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: state (type: string) + outputColumnNames: state Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: loc_orc + alias: null-subquery2:temp-subquery2:loc_orc Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string) - outputColumnNames: _col0 + outputColumnNames: state Statistics: Num rows: 8 Data size: 688 Basic stats: COMPLETE Column stats: COMPLETE Union Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: state (type: string) + outputColumnNames: state Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -370,37 +394,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: loc_staging + alias: null-subquery1:temp-subquery1:loc_staging Statistics: Num rows: 8 Data size: 109 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string) - outputColumnNames: _col0 + outputColumnNames: state Statistics: Num rows: 8 Data size: 688 Basic stats: COMPLETE Column stats: COMPLETE Union Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: state (type: string) + outputColumnNames: state Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: loc_orc + alias: null-subquery2:temp-subquery2:loc_orc Statistics: Num rows: 8 Data size: 796 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string) - outputColumnNames: _col0 + outputColumnNames: state Statistics: Num rows: 8 Data size: 688 Basic stats: COMPLETE Column stats: COMPLETE Union Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: state (type: string) + outputColumnNames: state Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/ansi_sql_arithmetic.q.out b/ql/src/test/results/clientpositive/ansi_sql_arithmetic.q.out index 5e5a2f6..1baced8 100644 --- a/ql/src/test/results/clientpositive/ansi_sql_arithmetic.q.out +++ b/ql/src/test/results/clientpositive/ansi_sql_arithmetic.q.out @@ -17,7 +17,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (CAST( UDFToInteger(key) AS decimal(10,0)) / CAST( UDFToInteger(key) AS decimal(10,0))) (type: decimal(21,11)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 @@ -64,7 +64,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(UDFToInteger(key)) / UDFToDouble(UDFToInteger(key))) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 diff --git a/ql/src/test/results/clientpositive/array_map_access_nonconstant.q.out b/ql/src/test/results/clientpositive/array_map_access_nonconstant.q.out index 7442c05..76a62bf 100644 --- a/ql/src/test/results/clientpositive/array_map_access_nonconstant.q.out +++ b/ql/src/test/results/clientpositive/array_map_access_nonconstant.q.out @@ -35,7 +35,7 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: index (type: int), array[index] (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: index, _o__c1 Statistics: Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: NONE ListSink @@ -88,7 +88,7 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), data[key] (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, _o__c1 Statistics: Num rows: 4 Data size: 84 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/authorization_explain.q.java1.7.out b/ql/src/test/results/clientpositive/authorization_explain.q.java1.7.out index 8209c6a..38a7359 100644 --- a/ql/src/test/results/clientpositive/authorization_explain.q.java1.7.out +++ b/ql/src/test/results/clientpositive/authorization_explain.q.java1.7.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [src, srcpart]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT explain authorization select * from src join srcpart @@ -23,7 +23,7 @@ OPERATION: AUTHORIZATION_FAILURES: No privilege 'Select' found for inputs { database:default, table:src, columnName:key} No privilege 'Select' found for inputs { database:default, table:srcpart, columnName:key} -Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [src, srcpart]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain formatted authorization select * from src join srcpart PREHOOK: type: QUERY POSTHOOK: query: explain formatted authorization select * from src join srcpart diff --git a/ql/src/test/results/clientpositive/auto_join0.q.out b/ql/src/test/results/clientpositive/auto_join0.q.out index 10859b8..23524a8 100644 --- a/ql/src/test/results/clientpositive/auto_join0.q.out +++ b/ql/src/test/results/clientpositive/auto_join0.q.out @@ -1,5 +1,5 @@ -Warning: Map Join MAPJOIN[45][bigTable=?] in task 'Stage-7:MAPRED' is a cross product -Warning: Map Join MAPJOIN[38][bigTable=?] in task 'Stage-6:MAPRED' is a cross product +Warning: Map Join MAPJOIN[47][bigTable=?] in task 'Stage-7:MAPRED' is a cross product +Warning: Map Join MAPJOIN[39][bigTable=?] in task 'Stage-6:MAPRED' is a cross product Warning: Shuffle Join JOIN[12][tables = [src1, src2]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: -- SORT_QUERY_RESULTS @@ -99,12 +99,16 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -147,13 +151,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-10 Map Reduce Local Work @@ -181,12 +189,16 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -212,12 +224,16 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-5 Map Reduce @@ -254,8 +270,8 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[45][bigTable=?] in task 'Stage-7:MAPRED' is a cross product -Warning: Map Join MAPJOIN[38][bigTable=?] in task 'Stage-6:MAPRED' is a cross product +Warning: Map Join MAPJOIN[47][bigTable=?] in task 'Stage-7:MAPRED' is a cross product +Warning: Map Join MAPJOIN[39][bigTable=?] in task 'Stage-6:MAPRED' is a cross product Warning: Shuffle Join JOIN[12][tables = [src1, src2]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: select sum(hash(a.k1,a.v1,a.k2, a.v2)) from ( diff --git a/ql/src/test/results/clientpositive/auto_join1.q.out b/ql/src/test/results/clientpositive/auto_join1.q.out index 48ad641..0b60f0c 100644 --- a/ql/src/test/results/clientpositive/auto_join1.q.out +++ b/ql/src/test/results/clientpositive/auto_join1.q.out @@ -28,25 +28,25 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:src1 + src2 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:src1 + src2 TableScan - alias: src1 + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-4 Map Reduce @@ -59,18 +59,18 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col2) (type: int), _col1 (type: string) + expressions: UDFToInteger(key0) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -108,7 +108,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest_j1 POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT sum(hash(dest_j1.key,dest_j1.value)) FROM dest_j1 PREHOOK: type: QUERY PREHOOK: Input: default@dest_j1 diff --git a/ql/src/test/results/clientpositive/auto_join10.q.out b/ql/src/test/results/clientpositive/auto_join10.q.out index fa6f62d..ae3b3eb 100644 --- a/ql/src/test/results/clientpositive/auto_join10.q.out +++ b/ql/src/test/results/clientpositive/auto_join10.q.out @@ -23,53 +23,53 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:src + y:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:src + y:src TableScan - alias: src + alias: y:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: src + alias: x:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0,_col1) (type: int) - outputColumnNames: _col0 + expressions: hash(key,value) (type: int) + outputColumnNames: $f0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -83,15 +83,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_join11.q.out b/ql/src/test/results/clientpositive/auto_join11.q.out index 851920b..7d4ce7b 100644 --- a/ql/src/test/results/clientpositive/auto_join11.q.out +++ b/ql/src/test/results/clientpositive/auto_join11.q.out @@ -23,53 +23,53 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:src + src2:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:src + src2:src TableScan - alias: src + alias: src2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col2,_col1) (type: int) - outputColumnNames: _col0 + expressions: hash(key0,value) (type: int) + outputColumnNames: $f0 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -83,15 +83,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_join12.q.out b/ql/src/test/results/clientpositive/auto_join12.q.out index 7d8db0a..8cd55bf 100644 --- a/ql/src/test/results/clientpositive/auto_join12.q.out +++ b/ql/src/test/results/clientpositive/auto_join12.q.out @@ -21,109 +21,120 @@ JOIN ON src1.c1 = src3.c5 AND src3.c5 < 80 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-7 is a root stage - Stage-2 depends on stages: Stage-7 - Stage-0 depends on stages: Stage-2 + Stage-8 is a root stage + Stage-3 depends on stages: Stage-8 + Stage-0 depends on stages: Stage-3 STAGE PLANS: - Stage: Stage-7 + Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_0:src + src1:src Fetch Operator limit: -1 - $hdt$_0:$hdt$_1:$hdt$_1:src + src3:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_0:src + src1:src TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 80.0) and (UDFToDouble(key) < 100.0)) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(key) < 100.0) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - $hdt$_0:$hdt$_1:$hdt$_1:src + 0 key (type: string) + 1 key (type: string) + src3:src TableScan - alias: src + alias: src3:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean) + predicate: ((UDFToDouble(key) < 80.0) and (UDFToDouble(key) < 100.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) - Stage: Stage-2 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: src + alias: src2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(key) < 100.0) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col3 - Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean) + Statistics: Num rows: 20 Data size: 213 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col1,_col3) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 20 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hash(key,value) (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum($f0) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_join13.q.out b/ql/src/test/results/clientpositive/auto_join13.q.out index 952dbf8..b45822f 100644 --- a/ql/src/test/results/clientpositive/auto_join13.q.out +++ b/ql/src/test/results/clientpositive/auto_join13.q.out @@ -29,82 +29,82 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:src + src2:src Fetch Operator limit: -1 - $hdt$_0:$hdt$_1:src + src3:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:src + src2:src TableScan - alias: src + alias: src2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) < 200.0) and UDFToDouble(key) is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(key) < 100.0) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) - 1 UDFToDouble(_col0) (type: double) - $hdt$_0:$hdt$_1:src + 0 key (type: string) + 1 key (type: string) + src3:src TableScan - alias: src + alias: src3:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(key) < 100.0) (type: boolean) + predicate: (UDFToDouble(key) < 200.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 (UDFToDouble(key0) + UDFToDouble(key)) (type: double) + 1 UDFToDouble(key) (type: double) Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(_col2) + UDFToDouble(_col0)) is not null (type: boolean) - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key0) + UDFToDouble(key)) < 200.0) (type: boolean) + Statistics: Num rows: 60 Data size: 639 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE + 0 (UDFToDouble(key0) + UDFToDouble(key)) (type: double) + 1 UDFToDouble(key) (type: double) + outputColumnNames: value, key0 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col2,_col1) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE + expressions: hash(key0,value) (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -118,15 +118,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_join14.q.out b/ql/src/test/results/clientpositive/auto_join14.q.out index 47e1724..db212d3 100644 --- a/ql/src/test/results/clientpositive/auto_join14.q.out +++ b/ql/src/test/results/clientpositive/auto_join14.q.out @@ -28,11 +28,11 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:src + src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:src + src TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -41,12 +41,12 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-4 Map Reduce @@ -59,18 +59,18 @@ STAGE PLANS: Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col3) (type: int), _col1 (type: string) + expressions: UDFToInteger(key0) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/auto_join15.q.out b/ql/src/test/results/clientpositive/auto_join15.q.out index 8e4b24c..22141ce 100644 --- a/ql/src/test/results/clientpositive/auto_join15.q.out +++ b/ql/src/test/results/clientpositive/auto_join15.q.out @@ -98,13 +98,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_join16.q.out b/ql/src/test/results/clientpositive/auto_join16.q.out index 1bad0f9..fc53a80 100644 --- a/ql/src/test/results/clientpositive/auto_join16.q.out +++ b/ql/src/test/results/clientpositive/auto_join16.q.out @@ -23,53 +23,53 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:a + subq:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_0:a + subq:a TableScan - alias: a + alias: subq:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) > 20.0)) and (UDFToDouble(value) < 200.0)) and key is not null) and value is not null) (type: boolean) - Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + predicate: (((((UDFToDouble(key) > 10.0) and value is not null) and key is not null) and (UDFToDouble(key) > 20.0)) and (UDFToDouble(value) < 200.0)) (type: boolean) + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) + 0 key (type: string), value (type: string) + 1 key (type: string), value (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: a + alias: tab Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(value) < 200.0) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) > 20.0)) and key is not null) and value is not null) (type: boolean) - Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + predicate: ((((value is not null and key is not null) and (UDFToDouble(value) < 200.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) > 20.0)) (type: boolean) + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 5 Data size: 58 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string), value (type: string) + 1 key (type: string), value (type: string) + outputColumnNames: key, value0 + Statistics: Num rows: 4 Data size: 46 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0,_col3) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 58 Basic stats: COMPLETE Column stats: NONE + expressions: hash(key,value0) (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 4 Data size: 46 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -83,15 +83,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_join17.q.out b/ql/src/test/results/clientpositive/auto_join17.q.out index e85cae8..351699d 100644 --- a/ql/src/test/results/clientpositive/auto_join17.q.out +++ b/ql/src/test/results/clientpositive/auto_join17.q.out @@ -24,11 +24,11 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:src1 + src1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:src1 + src1 TableScan alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -37,36 +37,36 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string), UDFToInteger(key0) (type: int), value0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -104,9 +104,9 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.key1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.key2 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.key2 EXPRESSION [(src)src2.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest1.value1 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.value2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.value2 SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT sum(hash(dest1.key1,dest1.value1,dest1.key2,dest1.value2)) FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git a/ql/src/test/results/clientpositive/auto_join18.q.out b/ql/src/test/results/clientpositive/auto_join18.q.out index 6dc7a63..c25bcc6 100644 --- a/ql/src/test/results/clientpositive/auto_join18.q.out +++ b/ql/src/test/results/clientpositive/auto_join18.q.out @@ -36,15 +36,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: a:src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -59,7 +59,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -73,33 +73,33 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, key0, $f10 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0,_col1,_col2,_col3) (type: int) - outputColumnNames: _col0 + expressions: hash(key,$f1,key0,$f10) (type: int) + outputColumnNames: $f0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -122,29 +122,33 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: src2 + alias: b:src2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT value) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -158,7 +162,7 @@ STAGE PLANS: aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out b/ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out index cc17ad1..4811e19 100644 --- a/ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out @@ -38,15 +38,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: a:src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -61,7 +61,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -75,33 +75,33 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint), _col2 (type: bigint) + value expressions: $f1 (type: bigint), $f2 (type: bigint) Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, key0, $f10, $f2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0,_col1,_col2,_col3,_col4) (type: int) - outputColumnNames: _col0 + expressions: hash(key,$f1,key0,$f10,$f2) (type: int) + outputColumnNames: $f0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -124,29 +124,33 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: src2 + alias: b:src2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), count(DISTINCT _col0) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT value), count(DISTINCT key) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -160,7 +164,7 @@ STAGE PLANS: aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, $f1, $f2 Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/auto_join19.q.out b/ql/src/test/results/clientpositive/auto_join19.q.out index 8a57cb0..4526131 100644 --- a/ql/src/test/results/clientpositive/auto_join19.q.out +++ b/ql/src/test/results/clientpositive/auto_join19.q.out @@ -26,11 +26,11 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:src2 + src2 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:src2 + src2 TableScan alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -39,12 +39,12 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-4 Map Reduce @@ -57,18 +57,18 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col4 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col4 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/auto_join2.q.out b/ql/src/test/results/clientpositive/auto_join2.q.out index abfc611..fb0be9b 100644 --- a/ql/src/test/results/clientpositive/auto_join2.q.out +++ b/ql/src/test/results/clientpositive/auto_join2.q.out @@ -15,23 +15,23 @@ FROM src src1 JOIN src src2 ON (src1.key = src2.key) JOIN src src3 ON (src1.key INSERT OVERWRITE TABLE dest_j2 SELECT src1.key, src3.value POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-6 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-6 - Stage-3 depends on stages: Stage-0 + Stage-7 is a root stage + Stage-5 depends on stages: Stage-7 + Stage-0 depends on stages: Stage-5 + Stage-2 depends on stages: Stage-0 STAGE PLANS: - Stage: Stage-8 + Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:src1 + src1 Fetch Operator limit: -1 - $hdt$_2:src1 + src3 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:src1 + src1 TableScan alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -40,72 +40,69 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - $hdt$_2:src1 + 0 key (type: string) + 1 key (type: string) + src3 TableScan - alias: src1 + alias: src3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: UDFToDouble(key) is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) + 0 UDFToDouble(key) (type: double) + 1 (UDFToDouble(key) + UDFToDouble(key0)) (type: double) - Stage: Stage-6 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col3 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest_j2 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 UDFToDouble(key) (type: double) + 1 (UDFToDouble(key) + UDFToDouble(key0)) (type: double) + outputColumnNames: value, key0 + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: UDFToInteger(key0) (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_j2 Local Work: Map Reduce Local Work @@ -119,7 +116,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j2 - Stage: Stage-3 + Stage: Stage-2 Stats-Aggr Operator PREHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key) JOIN src src3 ON (src1.key + src2.key = src3.key) @@ -133,7 +130,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest_j2 POSTHOOK: Lineage: dest_j2.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j2.value SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j2.value SIMPLE [(src)src3.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT sum(hash(dest_j2.key,dest_j2.value)) FROM dest_j2 PREHOOK: type: QUERY PREHOOK: Input: default@dest_j2 diff --git a/ql/src/test/results/clientpositive/auto_join20.q.out b/ql/src/test/results/clientpositive/auto_join20.q.out index 5247bf1..233570e 100644 --- a/ql/src/test/results/clientpositive/auto_join20.q.out +++ b/ql/src/test/results/clientpositive/auto_join20.q.out @@ -125,13 +125,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -285,13 +289,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_join22.q.out b/ql/src/test/results/clientpositive/auto_join22.q.out index bdee886..c7b5af6 100644 --- a/ql/src/test/results/clientpositive/auto_join22.q.out +++ b/ql/src/test/results/clientpositive/auto_join22.q.out @@ -5,109 +5,109 @@ POSTHOOK: query: explain SELECT sum(hash(src5.src1_value)) FROM (SELECT src3.*, src4.value as src4_value, src4.key as src4_key FROM src src4 JOIN (SELECT src2.*, src1.key as src1_key, src1.value as src1_value FROM src src1 JOIN src src2 ON src1.key = src2.key) src3 ON src3.src1_key = src4.key) src5 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-3 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-3 + Stage-6 is a root stage + Stage-2 depends on stages: Stage-6 + Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-8 + Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_0:src4 + src5:src3:src1 Fetch Operator limit: -1 - $hdt$_0:$hdt$_1:src4 + src5:src3:src2 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_0:src4 + src5:src3:src1 TableScan - alias: src4 + alias: src5:src3:src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - $hdt$_0:$hdt$_1:src4 + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + src5:src3:src2 TableScan - alias: src4 + alias: src5:src3:src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) - Stage: Stage-3 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: src4 + alias: src5:src4 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 + Inner Join 0 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hash(_col1) (type: int) + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: value + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hash(value) (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum($f0) + mode: hash outputColumnNames: _col0 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0) - mode: hash - outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_join24.q.out b/ql/src/test/results/clientpositive/auto_join24.q.out index 5b57303..5a2dfcd 100644 --- a/ql/src/test/results/clientpositive/auto_join24.q.out +++ b/ql/src/test/results/clientpositive/auto_join24.q.out @@ -66,15 +66,19 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col1 Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: _col1 (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col1) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -83,13 +87,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_join25.q.out b/ql/src/test/results/clientpositive/auto_join25.q.out index cc9a348..9f2dcd9 100644 --- a/ql/src/test/results/clientpositive/auto_join25.q.out +++ b/ql/src/test/results/clientpositive/auto_join25.q.out @@ -74,15 +74,15 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest_j2 POSTHOOK: Lineage: dest_j2.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j2.value SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -RUN: Stage-11:CONDITIONAL -RUN: Stage-14:MAPREDLOCAL -RUN: Stage-1:MAPRED -RUN: Stage-8:CONDITIONAL +POSTHOOK: Lineage: dest_j2.value SIMPLE [(src)src3.FieldSchema(name:value, type:string, comment:default), ] +RUN: Stage-10:CONDITIONAL +RUN: Stage-13:MAPREDLOCAL +RUN: Stage-3:MAPRED +RUN: Stage-7:CONDITIONAL RUN: Stage-12:MAPREDLOCAL -RUN: Stage-2:MAPRED +RUN: Stage-1:MAPRED RUN: Stage-0:MOVE -RUN: Stage-3:STATS +RUN: Stage-2:STATS PREHOOK: query: SELECT sum(hash(dest_j2.key,dest_j2.value)) FROM dest_j2 PREHOOK: type: QUERY PREHOOK: Input: default@dest_j2 @@ -115,7 +115,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest_j1 POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ] RUN: Stage-6:CONDITIONAL RUN: Stage-7:MAPREDLOCAL RUN: Stage-1:MAPRED diff --git a/ql/src/test/results/clientpositive/auto_join26.q.out b/ql/src/test/results/clientpositive/auto_join26.q.out index 94ab76f..2a49148 100644 --- a/ql/src/test/results/clientpositive/auto_join26.q.out +++ b/ql/src/test/results/clientpositive/auto_join26.q.out @@ -28,11 +28,11 @@ STAGE PLANS: Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:x + x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:x + x TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -41,12 +41,12 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-2 Map Reduce @@ -59,23 +59,23 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE @@ -92,10 +92,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) + expressions: UDFToInteger($f0) (type: int), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/auto_join27.q.out b/ql/src/test/results/clientpositive/auto_join27.q.out index 16a7f02..db155ce 100644 --- a/ql/src/test/results/clientpositive/auto_join27.q.out +++ b/ql/src/test/results/clientpositive/auto_join27.q.out @@ -34,17 +34,17 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery2:src_12-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 200.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -57,11 +57,11 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -73,38 +73,38 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:src + src3:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:src + src3:src TableScan - alias: src + alias: src3:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 200.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-6 Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1:src_12-subquery1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 200.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 249 Data size: 2644 Basic stats: COMPLETE Column stats: NONE @@ -112,20 +112,24 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Statistics: Num rows: 273 Data size: 2908 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 273 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f0) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan Union Statistics: Num rows: 249 Data size: 2644 Basic stats: COMPLETE Column stats: NONE @@ -133,20 +137,24 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Statistics: Num rows: 273 Data size: 2908 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 273 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f0) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -162,15 +170,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_join3.q.out b/ql/src/test/results/clientpositive/auto_join3.q.out index d015449..b08f43a 100644 --- a/ql/src/test/results/clientpositive/auto_join3.q.out +++ b/ql/src/test/results/clientpositive/auto_join3.q.out @@ -24,14 +24,14 @@ STAGE PLANS: Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:src1 + src1 Fetch Operator limit: -1 - $hdt$_1:src1 + src2 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:src1 + src1 TableScan alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -40,55 +40,55 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - $hdt$_1:src1 + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + src2 TableScan - alias: src1 + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) Stage: Stage-5 Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: src3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col3 + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: key, value1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col3 (type: string) + expressions: UDFToInteger(key) (type: int), value1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -126,7 +126,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.value SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.value SIMPLE [(src)src3.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT sum(hash(dest1.key,dest1.value)) FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git a/ql/src/test/results/clientpositive/auto_join30.q.out b/ql/src/test/results/clientpositive/auto_join30.q.out index 5437b7f..bf34bae 100644 --- a/ql/src/test/results/clientpositive/auto_join30.q.out +++ b/ql/src/test/results/clientpositive/auto_join30.q.out @@ -85,17 +85,21 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -113,13 +117,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-9 Map Reduce Local Work @@ -147,17 +155,21 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -186,17 +198,21 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -335,17 +351,21 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -363,13 +383,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-2 Map Reduce @@ -396,17 +420,21 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -542,17 +570,21 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -570,13 +602,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-2 Map Reduce @@ -603,17 +639,21 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -776,17 +816,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -804,13 +848,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-11 Map Reduce Local Work @@ -851,17 +899,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -904,17 +956,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -951,17 +1007,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -1158,17 +1218,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -1186,13 +1250,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-10 Map Reduce Local Work @@ -1233,17 +1301,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -1280,17 +1352,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -1479,17 +1555,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -1507,13 +1587,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-2 Map Reduce @@ -1548,17 +1632,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -1747,17 +1835,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -1775,13 +1867,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-2 Map Reduce @@ -1816,17 +1912,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -2015,17 +2115,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -2043,13 +2147,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-2 Map Reduce @@ -2084,17 +2192,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce diff --git a/ql/src/test/results/clientpositive/auto_join31.q.out b/ql/src/test/results/clientpositive/auto_join31.q.out index 0b25134..6a9c22d 100644 --- a/ql/src/test/results/clientpositive/auto_join31.q.out +++ b/ql/src/test/results/clientpositive/auto_join31.q.out @@ -102,17 +102,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -130,13 +134,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-10 Map Reduce Local Work @@ -177,17 +185,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -224,17 +236,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce diff --git a/ql/src/test/results/clientpositive/auto_join32.q.out b/ql/src/test/results/clientpositive/auto_join32.q.out index f862870..79a29fe 100644 --- a/ql/src/test/results/clientpositive/auto_join32.q.out +++ b/ql/src/test/results/clientpositive/auto_join32.q.out @@ -68,17 +68,21 @@ STAGE PLANS: 1 name (type: string) outputColumnNames: _col0, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: count(DISTINCT _col8) - keys: _col0 (type: string), _col8 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: _col0 (type: string), _col8 (type: string) + outputColumnNames: _col0, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: count(DISTINCT _col8) + keys: _col0 (type: string), _col8 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -88,13 +92,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -167,27 +175,33 @@ STAGE PLANS: 0 name (type: string) 1 name (type: string) outputColumnNames: _col0, _col8 - Group By Operator - aggregations: count(DISTINCT _col8) - keys: _col0 (type: string), _col8 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: _col0 (type: string), _col8 (type: string) + outputColumnNames: _col0, _col8 + Group By Operator + aggregations: count(DISTINCT _col8) + keys: _col0 (type: string), _col8 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -274,27 +288,33 @@ STAGE PLANS: 0 name (type: string) 1 name (type: string) outputColumnNames: _col0, _col8 - Group By Operator - aggregations: count(DISTINCT _col8) - keys: _col0 (type: string), _col8 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: _col0 (type: string), _col8 (type: string) + outputColumnNames: _col0, _col8 + Group By Operator + aggregations: count(DISTINCT _col8) + keys: _col0 (type: string), _col8 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -393,46 +413,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: v + alias: s Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((p = 'bar') and name is not null) (type: boolean) + predicate: (name is not null and (p = 'bar')) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: name (type: string), registration (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col3 - Select Operator - expressions: _col3 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 name (type: string) + 1 name (type: string) + outputColumnNames: _col0, _col9 + Select Operator + expressions: _col0 (type: string), _col9 (type: string) + outputColumnNames: _col0, _col9 + Group By Operator + aggregations: count(DISTINCT _col9) + keys: _col0 (type: string), _col9 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_join33.q.out b/ql/src/test/results/clientpositive/auto_join33.q.out index 0dcd91d..b603c7e 100644 --- a/ql/src/test/results/clientpositive/auto_join33.q.out +++ b/ql/src/test/results/clientpositive/auto_join33.q.out @@ -25,54 +25,58 @@ STAGE PLANS: Stage: Stage-4 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:src + a:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:src + a:src TableScan - alias: src + alias: a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) + 1.0) < 10.0) and (UDFToDouble(key) + 1.0) is not null) (type: boolean) + predicate: (((UDFToDouble(key) + 1.0) < 10.0) and key is not null) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 (UDFToDouble(_col0) + 1.0) (type: double) - 1 (UDFToDouble(_col0) + 2.0) (type: double) + 0 (UDFToDouble(key) + UDFToDouble(1)) (type: double) + 1 (UDFToDouble(key) + UDFToDouble(2)) (type: double) Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: src + alias: b:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) + 2.0) < 10.0) and (UDFToDouble(key) + 2.0) is not null) (type: boolean) + predicate: (((UDFToDouble(key) + 2.0) < 10.0) and key is not null) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col0) + 1.0) (type: double) - 1 (UDFToDouble(_col0) + 2.0) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 (UDFToDouble(key) + UDFToDouble(1)) (type: double) + 1 (UDFToDouble(key) + UDFToDouble(2)) (type: double) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/auto_join4.q.out b/ql/src/test/results/clientpositive/auto_join4.q.out index dbbee56..e4bfbc8 100644 --- a/ql/src/test/results/clientpositive/auto_join4.q.out +++ b/ql/src/test/results/clientpositive/auto_join4.q.out @@ -46,49 +46,49 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:$hdt$_1:src1 + c:b:src2 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:$hdt$_1:src1 + c:b:src2 TableScan - alias: src1 + alias: c:b:src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: c:a:src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string), UDFToInteger(key0) (type: int), value0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -147,10 +147,10 @@ INSERT OVERWRITE TABLE dest1 SELECT c.c1, c.c2, c.c3, c.c4 POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)c:a:src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)c:a:src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)c:b:src2.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)c:b:src2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT sum(hash(dest1.c1,dest1.c2,dest1.c3,dest1.c4)) FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git a/ql/src/test/results/clientpositive/auto_join5.q.out b/ql/src/test/results/clientpositive/auto_join5.q.out index 3209d07..a4c048e 100644 --- a/ql/src/test/results/clientpositive/auto_join5.q.out +++ b/ql/src/test/results/clientpositive/auto_join5.q.out @@ -46,49 +46,49 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:src1 + c:a:src1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:src1 + c:a:src1 TableScan - alias: src1 + alias: c:a:src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 15.0)) and (UDFToDouble(key) < 25.0)) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: c:b:src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string), UDFToInteger(key0) (type: int), value0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -147,10 +147,10 @@ INSERT OVERWRITE TABLE dest1 SELECT c.c1, c.c2, c.c3, c.c4 POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)c:a:src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)c:a:src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)c:b:src2.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)c:b:src2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT sum(hash(dest1.c1,dest1.c2,dest1.c3,dest1.c4)) FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git a/ql/src/test/results/clientpositive/auto_join6.q.out b/ql/src/test/results/clientpositive/auto_join6.q.out index fa0b4ed..9001dd0 100644 --- a/ql/src/test/results/clientpositive/auto_join6.q.out +++ b/ql/src/test/results/clientpositive/auto_join6.q.out @@ -46,48 +46,48 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: c:a:src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src1 + alias: c:b:src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string), UDFToInteger(key0) (type: int), value0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -144,10 +144,10 @@ INSERT OVERWRITE TABLE dest1 SELECT c.c1, c.c2, c.c3, c.c4 POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)c:a:src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)c:a:src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)c:b:src2.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)c:b:src2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT sum(hash(dest1.c1,dest1.c2,dest1.c3,dest1.c4)) FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git a/ql/src/test/results/clientpositive/auto_join7.q.out b/ql/src/test/results/clientpositive/auto_join7.q.out index 58e6298..e11297b 100644 --- a/ql/src/test/results/clientpositive/auto_join7.q.out +++ b/ql/src/test/results/clientpositive/auto_join7.q.out @@ -56,66 +56,66 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: c:a:src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src1 + alias: c:b:src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src1 + alias: c:c:src3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) > 20.0) and (UDFToDouble(key) < 25.0)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + predicate: ((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 20.0)) and (UDFToDouble(key) < 25.0)) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 Left Outer Join0 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: key, value, key0, value0, key1, value1 Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string), UDFToInteger(_col4) (type: int), _col5 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string), UDFToInteger(key0) (type: int), value0 (type: string), UDFToInteger(key1) (type: int), value1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -182,12 +182,12 @@ INSERT OVERWRITE TABLE dest1 SELECT c.c1, c.c2, c.c3, c.c4, c.c5, c.c6 POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c5 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c6 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)c:a:src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)c:a:src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)c:b:src2.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)c:b:src2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c5 EXPRESSION [(src)c:c:src3.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c6 SIMPLE [(src)c:c:src3.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT sum(hash(dest1.c1,dest1.c2,dest1.c3,dest1.c4,dest1.c5,dest1.c6)) FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git a/ql/src/test/results/clientpositive/auto_join8.q.out b/ql/src/test/results/clientpositive/auto_join8.q.out index 2ca26aa..798561d 100644 --- a/ql/src/test/results/clientpositive/auto_join8.q.out +++ b/ql/src/test/results/clientpositive/auto_join8.q.out @@ -46,52 +46,52 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:$hdt$_1:src1 + c:b:src2 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:$hdt$_1:src1 + c:b:src2 TableScan - alias: src1 + alias: c:b:src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: c:a:src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col2 is null (type: boolean) + predicate: key0 is null (type: boolean) Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), null (type: int), _col3 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string), null (type: int), value0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -150,10 +150,10 @@ INSERT OVERWRITE TABLE dest1 SELECT c.c1, c.c2, c.c3, c.c4 where c.c3 IS NULL AN POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)c:a:src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)c:a:src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)c:b:src2.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)c:b:src2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT sum(hash(dest1.c1,dest1.c2,dest1.c3,dest1.c4)) FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git a/ql/src/test/results/clientpositive/auto_join9.q.out b/ql/src/test/results/clientpositive/auto_join9.q.out index 13dd5de..f9afabb 100644 --- a/ql/src/test/results/clientpositive/auto_join9.q.out +++ b/ql/src/test/results/clientpositive/auto_join9.q.out @@ -24,11 +24,11 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:src1 + src1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:src1 + src1 TableScan alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -37,12 +37,12 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-4 Map Reduce @@ -55,18 +55,18 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col4 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col4 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/auto_join_filters.q.out b/ql/src/test/results/clientpositive/auto_join_filters.q.out index a6720d9..828d79d 100644 --- a/ql/src/test/results/clientpositive/auto_join_filters.q.out +++ b/ql/src/test/results/clientpositive/auto_join_filters.q.out @@ -44,7 +44,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3080335 -Warning: Shuffle Join JOIN[6][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -330,7 +330,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3078400 -Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -339,7 +339,7 @@ POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a F POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### -3078400 +4939870 PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b ON a.key = b.value AND a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git a/ql/src/test/results/clientpositive/auto_join_nulls.q.out b/ql/src/test/results/clientpositive/auto_join_nulls.q.out index 4416f3e..b4fe5d7 100644 --- a/ql/src/test/results/clientpositive/auto_join_nulls.q.out +++ b/ql/src/test/results/clientpositive/auto_join_nulls.q.out @@ -14,7 +14,7 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in1.txt' INTO TABLE my POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@myinput1 -Warning: Map Join MAPJOIN[18][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -24,7 +24,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 13630578 -Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -34,7 +34,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 13630578 -Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git a/ql/src/test/results/clientpositive/auto_join_without_localtask.q.out b/ql/src/test/results/clientpositive/auto_join_without_localtask.q.out index 3d0067b..cede195 100644 --- a/ql/src/test/results/clientpositive/auto_join_without_localtask.q.out +++ b/ql/src/test/results/clientpositive/auto_join_without_localtask.q.out @@ -21,25 +21,25 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:a + b Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:a + b TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-4 Map Reduce @@ -52,22 +52,26 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -76,13 +80,13 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 40 @@ -98,11 +102,11 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:a + a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:a + a TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -111,40 +115,44 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-5 Map Reduce Map Operator Tree: TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -159,44 +167,48 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -263,137 +275,137 @@ POSTHOOK: query: explain select a.* from src a join src b on a.key=b.key join src c on a.value=c.value order by a.key, a.value limit 40 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-11 is a root stage , consists of Stage-14, Stage-15, Stage-1 - Stage-14 has a backup stage: Stage-1 - Stage-9 depends on stages: Stage-14 - Stage-8 depends on stages: Stage-1, Stage-9, Stage-10 , consists of Stage-12, Stage-7, Stage-2 - Stage-12 has a backup stage: Stage-2 + Stage-10 is a root stage , consists of Stage-13, Stage-14, Stage-3 + Stage-13 has a backup stage: Stage-3 + Stage-8 depends on stages: Stage-13 + Stage-7 depends on stages: Stage-3, Stage-8, Stage-9 , consists of Stage-5, Stage-12, Stage-1 + Stage-5 has a backup stage: Stage-1 + Stage-2 depends on stages: Stage-1, Stage-5, Stage-6 + Stage-12 has a backup stage: Stage-1 Stage-6 depends on stages: Stage-12 - Stage-3 depends on stages: Stage-2, Stage-6, Stage-7 - Stage-7 has a backup stage: Stage-2 - Stage-2 - Stage-15 has a backup stage: Stage-1 - Stage-10 depends on stages: Stage-15 Stage-1 - Stage-0 depends on stages: Stage-3 + Stage-14 has a backup stage: Stage-3 + Stage-9 depends on stages: Stage-14 + Stage-3 + Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-11 + Stage: Stage-10 Conditional Operator - Stage: Stage-14 + Stage: Stage-13 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:a + a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:a + a TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col1 (type: string) - 1 _col0 (type: string) + 0 value (type: string) + 1 value (type: string) - Stage: Stage-9 + Stage: Stage-8 Map Reduce Map Operator Tree: TableScan - alias: a + alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (value is not null and key is not null) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key, value0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work - Stage: Stage-8 + Stage: Stage-7 Conditional Operator - Stage: Stage-12 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_2:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_2:a + Stage: Stage-5 + Map Reduce + Map Operator Tree: TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0, value0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key0 (type: string), value0 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work + Alias -> Map Local Tables: + $INTNAME + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + $INTNAME + TableScan - Stage: Stage-3 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 40 Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE @@ -405,186 +417,207 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-7 - Map Reduce - Map Operator Tree: + Stage: Stage-12 + Map Reduce Local Work + Alias -> Map Local Tables: + b + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + b TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 + HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Local Work: - Map Reduce Local Work - Alias -> Map Local Tables: - $INTNAME - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $INTNAME - TableScan + 0 key (type: string) + 1 key (type: string) - Stage: Stage-2 + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0, value0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Select Operator + expressions: key0 (type: string), value0 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Map Reduce + Map Operator Tree: TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + TableScan + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + value expressions: value0 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0, value0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key0 (type: string), value0 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-15 + Stage: Stage-14 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:a + c Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:a + c TableScan - alias: a + alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (value is not null and key is not null) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col1 (type: string) - 1 _col0 (type: string) + 0 value (type: string) + 1 value (type: string) - Stage: Stage-10 + Stage: Stage-9 Map Reduce Map Operator Tree: TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key, value0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: a + alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (value is not null and key is not null) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key, value0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -600,13 +633,13 @@ POSTHOOK: query: select a.* from src a join src b on a.key=b.key join src c on a POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -RUN: Stage-11:CONDITIONAL -RUN: Stage-14:MAPREDLOCAL -RUN: Stage-9:MAPRED -RUN: Stage-8:CONDITIONAL +RUN: Stage-10:CONDITIONAL +RUN: Stage-13:MAPREDLOCAL +RUN: Stage-8:MAPRED +RUN: Stage-7:CONDITIONAL RUN: Stage-12:MAPREDLOCAL RUN: Stage-6:MAPRED -RUN: Stage-3:MAPRED +RUN: Stage-2:MAPRED 0 val_0 0 val_0 0 val_0 @@ -675,53 +708,56 @@ STAGE PLANS: Stage: Stage-14 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_2:a + a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_2:a + a TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(key) > 100.0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + predicate: ((key is not null and value is not null) and (UDFToDouble(key) > 100.0)) (type: boolean) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 value (type: string) + 1 value (type: string) Stage: Stage-9 Map Reduce Map Operator Tree: TableScan - alias: a + alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) > 100.0) and value is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key, value0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (UDFToDouble(key) > 100.0) (type: boolean) + Statistics: Num rows: 91 Data size: 966 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -731,25 +767,25 @@ STAGE PLANS: Stage: Stage-12 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:a + b Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:a + b TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(key) > 100.0) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col1 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-6 Map Reduce @@ -759,16 +795,20 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value0 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value0 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -777,14 +817,14 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 40 Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE @@ -800,29 +840,33 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(key) > 100.0) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value0 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value0 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work Alias -> Map Local Tables: @@ -838,64 +882,68 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 91 Data size: 966 Basic stats: COMPLETE Column stats: NONE + value expressions: value0 (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(key) > 100.0) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value0 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value0 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-15 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:a + c Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:a + c TableScan - alias: a + alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) > 100.0) and value is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 value (type: string) + 1 value (type: string) Stage: Stage-10 Map Reduce @@ -904,26 +952,29 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(key) > 100.0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + predicate: ((key is not null and value is not null) and (UDFToDouble(key) > 100.0)) (type: boolean) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key, value0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (UDFToDouble(key) > 100.0) (type: boolean) + Statistics: Num rows: 91 Data size: 966 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -931,51 +982,54 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) > 100.0) and value is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(key) > 100.0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + predicate: ((key is not null and value is not null) and (UDFToDouble(key) > 100.0)) (type: boolean) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key, value0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (UDFToDouble(key) > 100.0) (type: boolean) + Statistics: Num rows: 91 Data size: 966 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_smb_mapjoin_14.q.out b/ql/src/test/results/clientpositive/auto_smb_mapjoin_14.q.out index 1dc9cd0..356dd33 100644 --- a/ql/src/test/results/clientpositive/auto_smb_mapjoin_14.q.out +++ b/ql/src/test/results/clientpositive/auto_smb_mapjoin_14.q.out @@ -74,24 +74,28 @@ STAGE PLANS: keys: 0 key (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -158,16 +162,19 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -198,12 +205,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -297,28 +307,34 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -369,28 +385,34 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -484,24 +506,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -580,24 +606,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -700,24 +730,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -810,24 +844,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -919,17 +957,19 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -945,13 +985,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1016,24 +1060,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1106,24 +1154,28 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1210,24 +1262,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1347,13 +1403,16 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest2 Stage: Stage-8 Conditional Operator @@ -1607,26 +1666,32 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Select Operator + expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_1.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_1.q.out index 5114038..1a01c36 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_1.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_1.q.out @@ -165,15 +165,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 1 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -282,26 +283,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -386,15 +390,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 0 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -503,26 +508,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -683,15 +691,16 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 0 - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -849,26 +858,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-7 Map Reduce Local Work @@ -1005,15 +1017,16 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 1 - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -1170,26 +1183,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Map Reduce @@ -1210,15 +1226,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 0 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1327,26 +1344,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_10.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_10.q.out index e7f6de3..2ce9062 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_10.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_10.q.out @@ -120,17 +120,19 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) Statistics: Num rows: 6 Data size: 46 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 6 Data size: 46 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan alias: a Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -154,17 +156,19 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) Statistics: Num rows: 6 Data size: 46 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 6 Data size: 46 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -182,13 +186,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -257,19 +265,23 @@ STAGE PLANS: Filter Operator predicate: (key < 6) (type: boolean) Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - bucketGroup: true - keys: key (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: int) + outputColumnNames: key Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + Group By Operator + aggregations: count() + bucketGroup: true + keys: key (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -322,15 +334,17 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -339,13 +353,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_11.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_11.q.out index e6e7ef3..e280122 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_11.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_11.q.out @@ -231,17 +231,19 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 1 Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -398,27 +400,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -581,17 +587,19 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 1 Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -748,27 +756,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -937,17 +949,19 @@ STAGE PLANS: Position of Big Table: 1 Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -1057,27 +1071,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -1374,17 +1392,19 @@ STAGE PLANS: Position of Big Table: 2 Statistics: Num rows: 127 Data size: 12786 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 127 Data size: 12786 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -1494,27 +1514,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out index b2e782f..28e6614 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out @@ -488,17 +488,19 @@ STAGE PLANS: 1 Position of Big Table: 0 Statistics: Num rows: 69 Data size: 7032 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 69 Data size: 7032 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -705,27 +707,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_14.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_14.q.out index 33c56fd..a8eed11 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_14.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_14.q.out @@ -81,13 +81,14 @@ STAGE PLANS: keys: 0 key (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -95,12 +96,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Map Reduce @@ -114,24 +118,28 @@ STAGE PLANS: keys: 0 key (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -207,13 +215,14 @@ STAGE PLANS: keys: 0 key (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -221,12 +230,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Map Reduce @@ -240,24 +252,28 @@ STAGE PLANS: keys: 0 key (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_15.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_15.q.out index 460e5b1..af1abbe 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_15.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_15.q.out @@ -79,13 +79,14 @@ STAGE PLANS: keys: 0 key (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -93,12 +94,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Map Reduce @@ -112,24 +116,28 @@ STAGE PLANS: keys: 0 key (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -182,13 +190,14 @@ STAGE PLANS: keys: 0 key (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -196,12 +205,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Map Reduce @@ -215,24 +227,28 @@ STAGE PLANS: keys: 0 key (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_2.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_2.q.out index 210f1ab..37ba52b 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_2.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_2.q.out @@ -145,15 +145,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 0 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -262,26 +263,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -444,15 +448,16 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 0 - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -610,26 +615,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-7 Map Reduce Local Work @@ -766,15 +774,16 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 1 - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -931,26 +940,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Map Reduce @@ -971,15 +983,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 0 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1088,26 +1101,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_3.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_3.q.out index a307b13..85bc567 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_3.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_3.q.out @@ -145,15 +145,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 1 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -213,26 +214,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -317,15 +321,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 0 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -385,26 +390,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -611,15 +619,16 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 0 - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -775,26 +784,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-7 Map Reduce Local Work @@ -884,15 +896,16 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 1 - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -1049,26 +1062,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Map Reduce @@ -1089,15 +1105,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 0 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1157,26 +1174,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out index f4ceee7..5be6a6d 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out @@ -161,15 +161,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 1 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -229,26 +230,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -333,15 +337,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 0 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -401,26 +406,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -627,15 +635,16 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 0 - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -791,26 +800,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-7 Map Reduce Local Work @@ -900,15 +912,16 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 1 - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -1065,26 +1078,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Map Reduce @@ -1105,15 +1121,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 0 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1173,26 +1190,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_5.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_5.q.out index 230158b..889c10d 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_5.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_5.q.out @@ -132,15 +132,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 1 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -196,26 +197,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -294,15 +298,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 0 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -358,26 +363,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -485,15 +493,16 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 0 - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -589,26 +598,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-7 Map Reduce Local Work @@ -650,15 +662,16 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 1 - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -754,26 +767,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Map Reduce @@ -794,15 +810,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 0 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -858,26 +875,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out index 853f641..9c62e5a 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out @@ -132,16 +132,17 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 value (type: string) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -155,12 +156,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -235,16 +239,17 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 value (type: string) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -258,12 +263,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -338,16 +346,17 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 value (type: string) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -361,12 +370,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -462,17 +474,19 @@ STAGE PLANS: 1 UDFToDouble(key) (type: double) 2 UDFToDouble(key) (type: double) Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -490,13 +504,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-10 Map Reduce Local Work @@ -551,17 +569,19 @@ STAGE PLANS: 1 UDFToDouble(key) (type: double) 2 UDFToDouble(key) (type: double) Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -618,17 +638,19 @@ STAGE PLANS: 1 UDFToDouble(key) (type: double) 2 UDFToDouble(key) (type: double) Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -678,17 +700,19 @@ STAGE PLANS: 1 UDFToDouble(key) (type: double) 2 UDFToDouble(key) (type: double) Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -737,24 +761,28 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) 2 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -825,16 +853,17 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 value (type: string) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -848,12 +877,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -924,16 +956,17 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 value (type: string) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -947,12 +980,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1048,17 +1084,19 @@ STAGE PLANS: 1 UDFToDouble(key) (type: double) 2 UDFToDouble(key) (type: double) Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -1076,13 +1114,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-10 Map Reduce Local Work @@ -1137,17 +1179,19 @@ STAGE PLANS: 1 UDFToDouble(key) (type: double) 2 UDFToDouble(key) (type: double) Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -1204,17 +1248,19 @@ STAGE PLANS: 1 UDFToDouble(key) (type: double) 2 UDFToDouble(key) (type: double) Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -1264,17 +1310,19 @@ STAGE PLANS: 1 UDFToDouble(key) (type: double) 2 UDFToDouble(key) (type: double) Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -1368,13 +1416,14 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) 2 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1382,12 +1431,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-9 Map Reduce Local Work @@ -1441,13 +1493,14 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) 2 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1455,12 +1508,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-10 Map Reduce Local Work @@ -1514,13 +1570,14 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) 2 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1528,12 +1585,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Map Reduce @@ -1552,24 +1612,28 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) 2 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1640,16 +1704,17 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 value (type: string) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1663,12 +1728,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out index e1f3888..bb55838 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out @@ -178,15 +178,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 1 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -295,26 +296,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -401,15 +405,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 0 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -518,26 +523,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -746,15 +754,16 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 0 - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -959,26 +968,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-7 Map Reduce Local Work @@ -1115,15 +1127,16 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 1 - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -1328,26 +1341,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Map Reduce @@ -1368,15 +1384,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 0 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1485,26 +1502,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_8.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_8.q.out index 38ecdbe..4bcc80c 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_8.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_8.q.out @@ -178,15 +178,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 1 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -295,26 +296,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -401,15 +405,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 0 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -518,26 +523,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -748,15 +756,16 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 0 - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -961,26 +970,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-7 Map Reduce Local Work @@ -1117,15 +1129,16 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 1 - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -1330,26 +1343,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Map Reduce @@ -1370,15 +1386,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 0 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1487,26 +1504,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out index bbfa756..51db63b 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out @@ -74,24 +74,28 @@ STAGE PLANS: keys: 0 key (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -151,28 +155,34 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -248,16 +258,19 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -288,12 +301,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -392,28 +408,34 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-8 Conditional Operator @@ -541,28 +563,34 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -656,24 +684,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -752,24 +784,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -872,24 +908,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -982,24 +1022,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1093,15 +1137,17 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1110,13 +1156,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1181,24 +1231,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1257,24 +1311,28 @@ STAGE PLANS: keys: 0 key (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1349,24 +1407,28 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1453,24 +1515,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1568,13 +1634,14 @@ STAGE PLANS: keys: 0 key (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1582,12 +1649,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-7 Map Reduce Local Work @@ -1623,13 +1693,14 @@ STAGE PLANS: keys: 0 key (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1637,12 +1708,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Map Reduce @@ -1659,24 +1733,28 @@ STAGE PLANS: keys: 0 key (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1763,16 +1841,19 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1781,12 +1862,15 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-7 Map Reduce Local Work @@ -1823,16 +1907,19 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1841,12 +1928,15 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Map Reduce @@ -1864,28 +1954,34 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1988,16 +2084,19 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -2030,12 +2129,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-8 Map Reduce Local Work @@ -2072,16 +2174,19 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -2118,16 +2223,19 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -2275,16 +2383,19 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -2293,12 +2404,15 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-8 Conditional Operator @@ -2445,16 +2559,19 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -2463,12 +2580,15 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce @@ -2486,28 +2606,34 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-14 Conditional Operator @@ -2547,16 +2673,19 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -2565,12 +2694,15 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-20 Map Reduce Local Work @@ -2607,16 +2739,19 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -2625,12 +2760,15 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -2648,28 +2786,34 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -2794,13 +2938,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -2808,12 +2953,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-7 Map Reduce Local Work @@ -2857,13 +3005,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -2871,12 +3020,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Map Reduce @@ -2897,24 +3049,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -3020,13 +3176,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -3034,12 +3191,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-7 Map Reduce Local Work @@ -3079,13 +3239,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -3093,12 +3254,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Map Reduce @@ -3119,24 +3283,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -3270,13 +3438,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -3284,12 +3453,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-7 Map Reduce Local Work @@ -3333,13 +3505,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -3347,12 +3520,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Map Reduce @@ -3373,24 +3549,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -3514,13 +3694,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -3528,12 +3709,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-7 Map Reduce Local Work @@ -3577,13 +3761,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -3591,12 +3776,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Map Reduce @@ -3617,24 +3805,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -3726,13 +3918,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -3740,12 +3933,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-7 Map Reduce Local Work @@ -3785,13 +3981,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -3799,12 +3996,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Map Reduce @@ -3825,24 +4025,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -3932,13 +4136,14 @@ STAGE PLANS: keys: 0 key (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -3946,12 +4151,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-7 Map Reduce Local Work @@ -3991,13 +4199,14 @@ STAGE PLANS: keys: 0 key (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -4005,12 +4214,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Map Reduce @@ -4027,24 +4239,28 @@ STAGE PLANS: keys: 0 key (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -4172,13 +4388,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -4186,12 +4403,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-9 Map Reduce Local Work @@ -4257,13 +4477,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -4271,12 +4492,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-10 Map Reduce Local Work @@ -4342,13 +4566,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -4356,12 +4581,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Map Reduce @@ -4384,24 +4612,28 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -4515,13 +4747,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -4529,12 +4762,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-7 Map Reduce Local Work @@ -4574,13 +4810,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -4588,12 +4825,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Map Reduce @@ -4614,24 +4854,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/autogen_colalias.q.out b/ql/src/test/results/clientpositive/autogen_colalias.q.out index 896a468..758f7b3 100644 --- a/ql/src/test/results/clientpositive/autogen_colalias.q.out +++ b/ql/src/test/results/clientpositive/autogen_colalias.q.out @@ -26,16 +26,16 @@ PREHOOK: Input: default@dest_grouped_old1 POSTHOOK: query: describe dest_grouped_old1 POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@dest_grouped_old1 -c0 int +_o__c0 int zz int key string -c3 int -c4 bigint -c5 double -c6 bigint -c7 timestamp -c8 int -c9 int +_o__c3 int +_o__c4 bigint +_o__c5 double +_o__c6 bigint +_o__c7 timestamp +_o__c8 int +_o__c9 int PREHOOK: query: create table dest_grouped_old2 as select distinct src.key from src PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@src diff --git a/ql/src/test/results/clientpositive/binarysortable_1.q.out b/ql/src/test/results/clientpositive/binarysortable_1.q.out index 421fd2e..1ff2d1e 100644 --- a/ql/src/test/results/clientpositive/binarysortable_1.q.out +++ b/ql/src/test/results/clientpositive/binarysortable_1.q.out @@ -45,15 +45,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: mytable + alias: a:mytable Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string) + aggregations: sum(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE @@ -68,11 +68,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: regexp_replace(regexp_replace(regexp_replace(_col0, '', '^A'), '', '^@'), '', '^B') (type: string), _col1 (type: double) - outputColumnNames: _col0, _col1 + expressions: regexp_replace(regexp_replace(regexp_replace(key, '', '^A'), '', '^@'), '', '^B') (type: string), $f1 (type: double) + outputColumnNames: _o__c0, value Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/bucket1.q.out b/ql/src/test/results/clientpositive/bucket1.q.out index 8009514..7d99aa0 100644 --- a/ql/src/test/results/clientpositive/bucket1.q.out +++ b/ql/src/test/results/clientpositive/bucket1.q.out @@ -50,14 +50,14 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Map-reduce partition columns: UDFToInteger(_col0) (type: int) + Map-reduce partition columns: UDFToInteger(key) (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col0 (type: string), _col1 (type: string) + value expressions: key (type: string), value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### diff --git a/ql/src/test/results/clientpositive/bucket2.q.out b/ql/src/test/results/clientpositive/bucket2.q.out index 75de8a9..0e20fe5 100644 --- a/ql/src/test/results/clientpositive/bucket2.q.out +++ b/ql/src/test/results/clientpositive/bucket2.q.out @@ -50,14 +50,14 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Map-reduce partition columns: UDFToInteger(_col0) (type: int) + Map-reduce partition columns: UDFToInteger(key) (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col0 (type: string), _col1 (type: string) + value expressions: key (type: string), value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### diff --git a/ql/src/test/results/clientpositive/bucket3.q.out b/ql/src/test/results/clientpositive/bucket3.q.out index c459870..e232807 100644 --- a/ql/src/test/results/clientpositive/bucket3.q.out +++ b/ql/src/test/results/clientpositive/bucket3.q.out @@ -54,14 +54,14 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Map-reduce partition columns: UDFToInteger(_col0) (type: int) + Map-reduce partition columns: UDFToInteger(key) (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col0 (type: string), _col1 (type: string) + value expressions: key (type: string), value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### diff --git a/ql/src/test/results/clientpositive/bucket_groupby.q.out b/ql/src/test/results/clientpositive/bucket_groupby.q.out index 1b48d3a..fcc39df 100644 --- a/ql/src/test/results/clientpositive/bucket_groupby.q.out +++ b/ql/src/test/results/clientpositive/bucket_groupby.q.out @@ -58,12 +58,12 @@ STAGE PLANS: alias: clustergroupby Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -78,18 +78,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -163,12 +167,12 @@ STAGE PLANS: alias: clustergroupby Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -183,18 +187,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -242,12 +250,12 @@ STAGE PLANS: alias: clustergroupby Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: length(key) (type: int) - outputColumnNames: _col0 + expressions: length(key) (type: int), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int) + aggregations: count($f1) + keys: $f0 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -262,18 +270,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: int), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -312,12 +324,12 @@ STAGE PLANS: alias: clustergroupby Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: abs(length(key)) (type: int) - outputColumnNames: _col0 + expressions: abs(length(key)) (type: int), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int) + aggregations: count($f1) + keys: $f0 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -332,18 +344,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: int), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -384,12 +400,12 @@ STAGE PLANS: alias: clustergroupby Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 3 (type: int), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), 3 (type: int) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -404,11 +420,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: $f0 (type: string), $f2 (type: bigint) + outputColumnNames: key, _o__c1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -464,15 +480,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: clustergroupby + alias: subq:clustergroupby Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 + expressions: value (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -487,18 +503,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -544,12 +564,12 @@ STAGE PLANS: alias: clustergroupby Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -564,15 +584,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -919,12 +943,12 @@ STAGE PLANS: alias: clustergroupby Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 3 (type: int), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), 3 (type: int) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -939,11 +963,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: $f0 (type: string), $f2 (type: bigint) + outputColumnNames: key, _o__c1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1031,13 +1055,13 @@ STAGE PLANS: alias: clustergroupby Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f1) bucketGroup: true - keys: _col0 (type: string) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1052,18 +1076,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1109,12 +1137,12 @@ STAGE PLANS: alias: clustergroupby Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 + expressions: value (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1129,18 +1157,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1186,13 +1218,13 @@ STAGE PLANS: alias: clustergroupby Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f2) bucketGroup: true - keys: _col0 (type: string), _col1 (type: string) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1207,11 +1239,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: $f0 (type: string), $f2 (type: bigint) + outputColumnNames: key, _o__c1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -1320,13 +1352,13 @@ STAGE PLANS: alias: clustergroupby Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f1) bucketGroup: true - keys: _col0 (type: string) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1341,18 +1373,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1398,12 +1434,12 @@ STAGE PLANS: alias: clustergroupby Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + expressions: value (type: string), key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1418,11 +1454,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col2 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: $f1 (type: string), $f2 (type: bigint) + outputColumnNames: key, _o__c1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 diff --git a/ql/src/test/results/clientpositive/bucket_map_join_1.q.out b/ql/src/test/results/clientpositive/bucket_map_join_1.q.out index 42e6a3f..0449126 100644 --- a/ql/src/test/results/clientpositive/bucket_map_join_1.q.out +++ b/ql/src/test/results/clientpositive/bucket_map_join_1.q.out @@ -150,17 +150,19 @@ STAGE PLANS: 1 key (type: string), value (type: string) Position of Big Table: 0 Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -223,27 +225,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/bucket_map_join_2.q.out b/ql/src/test/results/clientpositive/bucket_map_join_2.q.out index af73309..6523b08 100644 --- a/ql/src/test/results/clientpositive/bucket_map_join_2.q.out +++ b/ql/src/test/results/clientpositive/bucket_map_join_2.q.out @@ -150,17 +150,19 @@ STAGE PLANS: 1 key (type: string), value (type: string) Position of Big Table: 0 Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -223,27 +225,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/bucketcontext_1.q.out b/ql/src/test/results/clientpositive/bucketcontext_1.q.out index 77bfcf9..0c89bb4 100644 --- a/ql/src/test/results/clientpositive/bucketcontext_1.q.out +++ b/ql/src/test/results/clientpositive/bucketcontext_1.q.out @@ -242,17 +242,19 @@ STAGE PLANS: Position of Big Table: 1 Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -364,27 +366,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -474,15 +480,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 1 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -591,26 +598,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/bucketcontext_2.q.out b/ql/src/test/results/clientpositive/bucketcontext_2.q.out index a9db13d..16aff4a 100644 --- a/ql/src/test/results/clientpositive/bucketcontext_2.q.out +++ b/ql/src/test/results/clientpositive/bucketcontext_2.q.out @@ -226,17 +226,19 @@ STAGE PLANS: Position of Big Table: 1 Statistics: Num rows: 31 Data size: 3196 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 31 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -348,27 +350,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -458,15 +464,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 1 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -575,26 +582,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/bucketcontext_3.q.out b/ql/src/test/results/clientpositive/bucketcontext_3.q.out index 9ba3e0c..3863f3d 100644 --- a/ql/src/test/results/clientpositive/bucketcontext_3.q.out +++ b/ql/src/test/results/clientpositive/bucketcontext_3.q.out @@ -272,17 +272,19 @@ STAGE PLANS: Position of Big Table: 1 Statistics: Num rows: 31 Data size: 3196 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 31 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -345,27 +347,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -455,15 +461,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 1 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -523,26 +530,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/bucketcontext_4.q.out b/ql/src/test/results/clientpositive/bucketcontext_4.q.out index a2b37a8..5ccccdd 100644 --- a/ql/src/test/results/clientpositive/bucketcontext_4.q.out +++ b/ql/src/test/results/clientpositive/bucketcontext_4.q.out @@ -288,17 +288,19 @@ STAGE PLANS: Position of Big Table: 1 Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -361,27 +363,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -471,15 +477,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 1 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -539,26 +546,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/bucketcontext_5.q.out b/ql/src/test/results/clientpositive/bucketcontext_5.q.out index 3ee1f0e..b8aa078 100644 --- a/ql/src/test/results/clientpositive/bucketcontext_5.q.out +++ b/ql/src/test/results/clientpositive/bucketcontext_5.q.out @@ -160,17 +160,19 @@ STAGE PLANS: Position of Big Table: 1 Statistics: Num rows: 31 Data size: 3196 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 31 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -229,27 +231,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -333,15 +339,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 1 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -397,26 +404,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/bucketcontext_6.q.out b/ql/src/test/results/clientpositive/bucketcontext_6.q.out index d2304fa..9ef53ae 100644 --- a/ql/src/test/results/clientpositive/bucketcontext_6.q.out +++ b/ql/src/test/results/clientpositive/bucketcontext_6.q.out @@ -178,17 +178,19 @@ STAGE PLANS: Position of Big Table: 1 Statistics: Num rows: 31 Data size: 3196 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 31 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -300,27 +302,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -408,15 +414,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 1 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -525,26 +532,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/bucketcontext_7.q.out b/ql/src/test/results/clientpositive/bucketcontext_7.q.out index 1a105ed..b00db63 100644 --- a/ql/src/test/results/clientpositive/bucketcontext_7.q.out +++ b/ql/src/test/results/clientpositive/bucketcontext_7.q.out @@ -305,17 +305,19 @@ STAGE PLANS: Position of Big Table: 1 Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -427,27 +429,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -539,15 +545,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 1 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -656,26 +663,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/bucketcontext_8.q.out b/ql/src/test/results/clientpositive/bucketcontext_8.q.out index 138e415..4eafe05 100644 --- a/ql/src/test/results/clientpositive/bucketcontext_8.q.out +++ b/ql/src/test/results/clientpositive/bucketcontext_8.q.out @@ -305,17 +305,19 @@ STAGE PLANS: Position of Big Table: 1 Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -427,27 +429,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -539,15 +545,16 @@ STAGE PLANS: 1 key (type: string) Position of Big Table: 1 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -656,26 +663,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/bucketmapjoin10.q.out b/ql/src/test/results/clientpositive/bucketmapjoin10.q.out index b0e849d..d598b0d 100644 --- a/ql/src/test/results/clientpositive/bucketmapjoin10.q.out +++ b/ql/src/test/results/clientpositive/bucketmapjoin10.q.out @@ -329,17 +329,19 @@ STAGE PLANS: 1 key (type: int) Position of Big Table: 0 Statistics: Num rows: 955 Data size: 3824 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 955 Data size: 3824 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -449,27 +451,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/bucketmapjoin11.q.out b/ql/src/test/results/clientpositive/bucketmapjoin11.q.out index 4263cab..34c6458 100644 --- a/ql/src/test/results/clientpositive/bucketmapjoin11.q.out +++ b/ql/src/test/results/clientpositive/bucketmapjoin11.q.out @@ -347,17 +347,19 @@ STAGE PLANS: Position of Big Table: 0 Statistics: Num rows: 1177 Data size: 4709 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 1177 Data size: 4709 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -467,27 +469,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -735,17 +741,19 @@ STAGE PLANS: Position of Big Table: 0 Statistics: Num rows: 1177 Data size: 4709 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 1177 Data size: 4709 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -855,27 +863,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/bucketmapjoin12.q.out b/ql/src/test/results/clientpositive/bucketmapjoin12.q.out index bcd7394..af10868 100644 --- a/ql/src/test/results/clientpositive/bucketmapjoin12.q.out +++ b/ql/src/test/results/clientpositive/bucketmapjoin12.q.out @@ -260,17 +260,19 @@ STAGE PLANS: Position of Big Table: 0 Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -332,27 +334,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -536,17 +542,19 @@ STAGE PLANS: 1 key (type: int) Position of Big Table: 0 Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -608,27 +616,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/bucketmapjoin13.q.out b/ql/src/test/results/clientpositive/bucketmapjoin13.q.out index 7114721..53b88fd 100644 --- a/ql/src/test/results/clientpositive/bucketmapjoin13.q.out +++ b/ql/src/test/results/clientpositive/bucketmapjoin13.q.out @@ -212,17 +212,19 @@ STAGE PLANS: 1 key (type: int) Position of Big Table: 0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -332,27 +334,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -540,17 +546,19 @@ STAGE PLANS: Position of Big Table: 0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -612,27 +620,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -819,17 +831,19 @@ STAGE PLANS: Position of Big Table: 0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -891,27 +905,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -1100,17 +1118,19 @@ STAGE PLANS: Position of Big Table: 0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -1172,27 +1192,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/bucketmapjoin8.q.out b/ql/src/test/results/clientpositive/bucketmapjoin8.q.out index 252b377..6be5447 100644 --- a/ql/src/test/results/clientpositive/bucketmapjoin8.q.out +++ b/ql/src/test/results/clientpositive/bucketmapjoin8.q.out @@ -226,17 +226,19 @@ STAGE PLANS: Position of Big Table: 0 Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -298,27 +300,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -519,17 +525,19 @@ STAGE PLANS: Position of Big Table: 0 Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -591,27 +599,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/bucketmapjoin9.q.out b/ql/src/test/results/clientpositive/bucketmapjoin9.q.out index 5e28dc3..68827b7 100644 --- a/ql/src/test/results/clientpositive/bucketmapjoin9.q.out +++ b/ql/src/test/results/clientpositive/bucketmapjoin9.q.out @@ -226,17 +226,19 @@ STAGE PLANS: 1 key (type: int) Position of Big Table: 0 Statistics: Num rows: 577 Data size: 2310 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 577 Data size: 2310 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -298,27 +300,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -544,17 +550,19 @@ STAGE PLANS: 1 key (type: int) Position of Big Table: 0 Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -616,27 +624,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/bucketsortoptimize_insert_1.q.out b/ql/src/test/results/clientpositive/bucketsortoptimize_insert_1.q.out index 9faa0d0..9ad6d93 100644 --- a/ql/src/test/results/clientpositive/bucketsortoptimize_insert_1.q.out +++ b/ql/src/test/results/clientpositive/bucketsortoptimize_insert_1.q.out @@ -60,11 +60,11 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: x:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -108,8 +108,8 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test_table1 POSTHOOK: Input: default@test_table1@ds=1 POSTHOOK: Output: default@test_table2@ds=1 -POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ] +POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key SIMPLE [(test_table1)x:a.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(test_table1)x:a.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: select count(*) from test_table2 where ds = '1' PREHOOK: type: QUERY PREHOOK: Input: default@test_table2 @@ -167,11 +167,11 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: x:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -215,8 +215,8 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test_table1 POSTHOOK: Input: default@test_table1@ds=1 POSTHOOK: Output: default@test_table2@ds=1 -POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ] +POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key SIMPLE [(test_table1)x:a.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(test_table1)x:a.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: select count(*) from test_table2 where ds = '1' PREHOOK: type: QUERY PREHOOK: Input: default@test_table2 @@ -276,11 +276,11 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: x:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), concat(value, value) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, _o__c1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -332,18 +332,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: x:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key + key) (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _o__c0, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _o__c0 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _o__c0 (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) @@ -399,11 +399,11 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: x:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), concat(value, value) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: k1, _o__c1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/bucketsortoptimize_insert_3.q.out b/ql/src/test/results/clientpositive/bucketsortoptimize_insert_3.q.out index e778e35..2b5adee 100644 --- a/ql/src/test/results/clientpositive/bucketsortoptimize_insert_3.q.out +++ b/ql/src/test/results/clientpositive/bucketsortoptimize_insert_3.q.out @@ -58,11 +58,11 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: x:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: value, key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -102,8 +102,8 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test_table1 POSTHOOK: Input: default@test_table1@ds=1 POSTHOOK: Output: default@test_table2@ds=1 -POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ] +POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key SIMPLE [(test_table1)x:a.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(test_table1)x:a.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: select count(*) from test_table2 where ds = '1' PREHOOK: type: QUERY PREHOOK: Input: default@test_table2 @@ -171,18 +171,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: x:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToInteger(_col1) (type: int) + key expressions: UDFToInteger(value) (type: int) sort order: + - Map-reduce partition columns: UDFToInteger(_col1) (type: int) + Map-reduce partition columns: UDFToInteger(value) (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string) + value expressions: key (type: int), value (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), UDFToInteger(VALUE._col1) (type: int) @@ -226,8 +226,8 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test_table1 POSTHOOK: Input: default@test_table1@ds=1 POSTHOOK: Output: default@test_table2@ds=1 -POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ] -POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(test_table1)x:a.FieldSchema(name:value, type:string, comment:null), ] +POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(test_table1)x:a.FieldSchema(name:key, type:int, comment:null), ] PREHOOK: query: select count(*) from test_table2 where ds = '1' PREHOOK: type: QUERY PREHOOK: Input: default@test_table2 diff --git a/ql/src/test/results/clientpositive/bucketsortoptimize_insert_4.q.out b/ql/src/test/results/clientpositive/bucketsortoptimize_insert_4.q.out index 594dc55..397873f 100644 --- a/ql/src/test/results/clientpositive/bucketsortoptimize_insert_4.q.out +++ b/ql/src/test/results/clientpositive/bucketsortoptimize_insert_4.q.out @@ -397,11 +397,14 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - value expressions: _col0 (type: int) + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + value expressions: _col0 (type: int) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -466,11 +469,14 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - value expressions: _col0 (type: int) + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + value expressions: _col0 (type: int) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -501,11 +507,14 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - value expressions: _col0 (type: int) + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + value expressions: _col0 (type: int) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), KEY.reducesinkkey0 (type: string) diff --git a/ql/src/test/results/clientpositive/cast1.q.out b/ql/src/test/results/clientpositive/cast1.q.out index 0bdecba..4f98981 100644 --- a/ql/src/test/results/clientpositive/cast1.q.out +++ b/ql/src/test/results/clientpositive/cast1.q.out @@ -34,7 +34,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 5 (type: int), 5.0 (type: double), 5.0 (type: double), 5.0 (type: double), 5 (type: int), true (type: boolean), 1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/cbo_rp_join1.q.out b/ql/src/test/results/clientpositive/cbo_rp_join1.q.out index 69ce6d2..eeabc78 100644 --- a/ql/src/test/results/clientpositive/cbo_rp_join1.q.out +++ b/ql/src/test/results/clientpositive/cbo_rp_join1.q.out @@ -14,7 +14,7 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in3.txt' INTO TABLE my POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@myinput1 -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: EXPLAIN SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b on a.key = 40 AND b.key = 40 PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b on a.key = 40 AND b.key = 40 @@ -31,46 +31,43 @@ STAGE PLANS: TableScan alias: a Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key = 40) (type: boolean) - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 40 (type: int), value (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int) + Select Operator + expressions: key (type: int), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: int), value (type: int) TableScan - alias: a + alias: b Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key = 40) (type: boolean) - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 40 (type: int), value (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int) + Select Operator + expressions: key (type: int), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: int), value (type: int) Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 + filter predicates: + 0 {(VALUE.key = 40)} + 1 {(VALUE.key = 40)} keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0,_col1,_col2,_col3) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + expressions: hash(key,value,key0,value0) (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -93,15 +90,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -109,7 +110,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b on a.key = 40 AND b.key = 40 PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -118,8 +119,8 @@ POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a F POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### -NULL -Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +4939870 +Warning: Shuffle Join JOIN[6][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: EXPLAIN SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b on a.key = 40 AND a.value = 40 AND a.key = a.value AND b.key = 40 PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b on a.key = 40 AND a.value = 40 AND a.key = a.value AND b.key = 40 @@ -136,46 +137,43 @@ STAGE PLANS: TableScan alias: a Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((key = 40) and (value = 40)) (type: boolean) - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 40 (type: int), 40 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int) + Select Operator + expressions: key (type: int), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: int), value (type: int) TableScan - alias: a + alias: b Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key = 40) (type: boolean) - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 40 (type: int), value (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int) + Select Operator + expressions: key (type: int), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: int), value (type: int) Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 + filter predicates: + 0 {(VALUE.key = 40)} {(VALUE.value = 40)} {(VALUE.key = VALUE.value)} + 1 {(VALUE.key = 40)} keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0,_col1,_col2,_col3) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + expressions: hash(key,value,key0,value0) (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -198,15 +196,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -214,7 +216,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b on a.key = 40 AND a.key = a.value AND b.key = 40 PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -223,7 +225,7 @@ POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a F POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### -NULL +4939870 PREHOOK: query: EXPLAIN SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b on a.key = 40 AND a.key = b.key AND b.key = 40 PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b on a.key = 40 AND a.key = b.key AND b.key = 40 @@ -270,17 +272,21 @@ STAGE PLANS: 1 key (type: int) outputColumnNames: _col0, _col1, _col5, _col6 Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0,_col1,_col5,_col6)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col6 (type: int) + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0,_col1,_col5,_col6)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -296,13 +302,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -319,7 +329,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### NULL -Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: EXPLAIN SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value @@ -336,46 +346,43 @@ STAGE PLANS: TableScan alias: a Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((key > 40) and (value > 50)) and (key = value)) (type: boolean) - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int) + Select Operator + expressions: key (type: int), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: int), value (type: int) TableScan - alias: a + alias: b Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((key > 40) and (value > 50)) and (key = value)) (type: boolean) - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int) + Select Operator + expressions: key (type: int), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: int), value (type: int) Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 + filter predicates: + 0 {(VALUE.key > 40)} {(VALUE.value > 50)} {(VALUE.key = VALUE.value)} + 1 {(VALUE.key > 40)} {(VALUE.value > 50)} {(VALUE.key = VALUE.value)} keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0,_col1,_col2,_col3) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + expressions: hash(key,value,key0,value0) (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -398,15 +405,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -414,7 +425,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -423,4 +434,4 @@ POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a F POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### -3078400 +4939870 diff --git a/ql/src/test/results/clientpositive/cluster.q.out b/ql/src/test/results/clientpositive/cluster.q.out index 2da1f91..5afbc32 100644 --- a/ql/src/test/results/clientpositive/cluster.q.out +++ b/ql/src/test/results/clientpositive/cluster.q.out @@ -508,12 +508,16 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -793,12 +797,16 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -876,12 +884,16 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -894,12 +906,16 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) diff --git a/ql/src/test/results/clientpositive/column_access_stats.q.out b/ql/src/test/results/clientpositive/column_access_stats.q.out index e904347..73dbd9f 100644 --- a/ql/src/test/results/clientpositive/column_access_stats.q.out +++ b/ql/src/test/results/clientpositive/column_access_stats.q.out @@ -91,11 +91,11 @@ STAGE PLANS: limit: -1 Processor Tree: TableScan - alias: t1 + alias: subq1:t1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE ListSink @@ -123,11 +123,11 @@ STAGE PLANS: limit: -1 Processor Tree: TableScan - alias: t1 + alias: subq1:t1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE ListSink @@ -187,37 +187,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: null-subquery1:subq1-subquery1:t1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: t1 + alias: null-subquery2:subq1-subquery2:t1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: val (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -264,37 +272,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: null-subquery1:subq1-subquery1:t1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: t1 + alias: null-subquery2:subq1-subquery2:t1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -400,13 +416,17 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -601,13 +621,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -702,12 +726,16 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -739,13 +767,17 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/columnstats_partlvl.q.out b/ql/src/test/results/clientpositive/columnstats_partlvl.q.out index e0c4cfe..6118617 100644 --- a/ql/src/test/results/clientpositive/columnstats_partlvl.q.out +++ b/ql/src/test/results/clientpositive/columnstats_partlvl.q.out @@ -623,12 +623,15 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: struct), _col1 (type: struct) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work diff --git a/ql/src/test/results/clientpositive/columnstats_quoting.q.out b/ql/src/test/results/clientpositive/columnstats_quoting.q.out index bd36ef0..613b5cc 100644 --- a/ql/src/test/results/clientpositive/columnstats_quoting.q.out +++ b/ql/src/test/results/clientpositive/columnstats_quoting.q.out @@ -39,12 +39,15 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: struct), _col1 (type: struct) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work @@ -90,12 +93,15 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: struct) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work diff --git a/ql/src/test/results/clientpositive/columnstats_tbllvl.q.out b/ql/src/test/results/clientpositive/columnstats_tbllvl.q.out index 19283bb..ee2af39 100644 --- a/ql/src/test/results/clientpositive/columnstats_tbllvl.q.out +++ b/ql/src/test/results/clientpositive/columnstats_tbllvl.q.out @@ -69,12 +69,15 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + outputColumnNames: _col0, _col1, _col2 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work @@ -178,26 +181,29 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types struct:struct:struct - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + outputColumnNames: _col0, _col1, _col2 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types struct:struct:struct + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Column Stats Work @@ -246,12 +252,15 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5), compute_stats(VALUE._col6), compute_stats(VALUE._col7), compute_stats(VALUE._col8) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work @@ -346,12 +355,15 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work @@ -470,12 +482,15 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + outputColumnNames: _col0, _col1, _col2 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work @@ -580,26 +595,29 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types struct:struct:struct - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + outputColumnNames: _col0, _col1, _col2 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types struct:struct:struct + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Column Stats Work @@ -648,12 +666,15 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5), compute_stats(VALUE._col6), compute_stats(VALUE._col7), compute_stats(VALUE._col8) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work diff --git a/ql/src/test/results/clientpositive/combine2.q.out b/ql/src/test/results/clientpositive/combine2.q.out index 9b1702f..19f4823 100644 --- a/ql/src/test/results/clientpositive/combine2.q.out +++ b/ql/src/test/results/clientpositive/combine2.q.out @@ -65,14 +65,14 @@ POSTHOOK: Output: default@combine2@value=val_5 POSTHOOK: Output: default@combine2@value=val_8 POSTHOOK: Output: default@combine2@value=val_9 POSTHOOK: Output: default@combine2@value=| -POSTHOOK: Lineage: combine2 PARTITION(value=2010-04-21 09:45:00).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: combine2 PARTITION(value=val_0).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: combine2 PARTITION(value=val_2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: combine2 PARTITION(value=val_4).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: combine2 PARTITION(value=val_5).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: combine2 PARTITION(value=val_8).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: combine2 PARTITION(value=val_9).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: combine2 PARTITION(value=|).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: combine2 PARTITION(value=2010-04-21 09:45:00).key EXPRESSION [(src)null-subquery1-subquery1:s-subquery1-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery2:s-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:s-subquery2:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: combine2 PARTITION(value=val_0).key EXPRESSION [(src)null-subquery1-subquery1:s-subquery1-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery2:s-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:s-subquery2:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: combine2 PARTITION(value=val_2).key EXPRESSION [(src)null-subquery1-subquery1:s-subquery1-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery2:s-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:s-subquery2:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: combine2 PARTITION(value=val_4).key EXPRESSION [(src)null-subquery1-subquery1:s-subquery1-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery2:s-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:s-subquery2:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: combine2 PARTITION(value=val_5).key EXPRESSION [(src)null-subquery1-subquery1:s-subquery1-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery2:s-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:s-subquery2:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: combine2 PARTITION(value=val_8).key EXPRESSION [(src)null-subquery1-subquery1:s-subquery1-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery2:s-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:s-subquery2:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: combine2 PARTITION(value=val_9).key EXPRESSION [(src)null-subquery1-subquery1:s-subquery1-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery2:s-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:s-subquery2:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: combine2 PARTITION(value=|).key EXPRESSION [(src)null-subquery1-subquery1:s-subquery1-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery2:s-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:s-subquery2:src.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: show partitions combine2 PREHOOK: type: SHOWPARTITIONS PREHOOK: Input: default@combine2 @@ -106,7 +106,7 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 14 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 12 Data size: 14 Basic stats: COMPLETE Column stats: NONE ListSink @@ -188,9 +188,11 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 14 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12 Data size: 14 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -564,42 +566,46 @@ STAGE PLANS: name: default.combine2 name: default.combine2 Truncated Path -> Alias: - /combine2/value=2010-04-21 09%3A45%3A00 [$hdt$_0:combine2] - /combine2/value=val_0 [$hdt$_0:combine2] - /combine2/value=val_2 [$hdt$_0:combine2] - /combine2/value=val_4 [$hdt$_0:combine2] - /combine2/value=val_5 [$hdt$_0:combine2] - /combine2/value=val_8 [$hdt$_0:combine2] - /combine2/value=val_9 [$hdt$_0:combine2] - /combine2/value=| [$hdt$_0:combine2] + /combine2/value=2010-04-21 09%3A45%3A00 [combine2] + /combine2/value=val_0 [combine2] + /combine2/value=val_2 [combine2] + /combine2/value=val_4 [combine2] + /combine2/value=val_5 [combine2] + /combine2/value=val_8 [combine2] + /combine2/value=val_9 [combine2] + /combine2/value=| [combine2] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns $f0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -650,12 +656,12 @@ STAGE PLANS: alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 + expressions: ds (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE @@ -670,15 +676,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/compute_stats_date.q.out b/ql/src/test/results/clientpositive/compute_stats_date.q.out index b57a862..54b3b8b 100644 --- a/ql/src/test/results/clientpositive/compute_stats_date.q.out +++ b/ql/src/test/results/clientpositive/compute_stats_date.q.out @@ -79,12 +79,15 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: struct) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work diff --git a/ql/src/test/results/clientpositive/constantPropagateForSubQuery.q.out b/ql/src/test/results/clientpositive/constantPropagateForSubQuery.q.out index b52b475..ecde0d9 100644 --- a/ql/src/test/results/clientpositive/constantPropagateForSubQuery.q.out +++ b/ql/src/test/results/clientpositive/constantPropagateForSubQuery.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[7][tables = [c:a, c:b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- SORT_QUERY_RESULTS explain extended @@ -80,7 +80,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: c:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator @@ -89,27 +89,27 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col1 (type: string) + value expressions: '429' (type: string), value (type: string) auto parallelism: false TableScan - alias: b + alias: c:b Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col0 (type: string), _col1 (type: string) + value expressions: key (type: string), value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -203,8 +203,8 @@ STAGE PLANS: name: default.src1 name: default.src1 Truncated Path -> Alias: - /src [$hdt$_0:a] - /src1 [$hdt$_1:b] + /src [c:a] + /src1 [c:b] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -213,11 +213,11 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col1, _col2, _col3 + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '429' (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -230,7 +230,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2,_col3 + columns key,value,key0,value0 columns.types string:string:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -247,7 +247,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[7][tables = [c:a, c:b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select * from (select a.key as ak, a.value as av, b.key as bk, b.value as bv from src a join src1 b where a.key = '429' ) c PREHOOK: type: QUERY PREHOOK: Input: default@src diff --git a/ql/src/test/results/clientpositive/constprog2.q.out b/ql/src/test/results/clientpositive/constprog2.q.out index 792b111..4114db3 100644 --- a/ql/src/test/results/clientpositive/constprog2.q.out +++ b/ql/src/test/results/clientpositive/constprog2.q.out @@ -15,21 +15,21 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: '86' (type: string) sort order: + Map-reduce partition columns: '86' (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -48,13 +48,13 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '86' (type: string), 87.0 (type: double), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key0 (type: string), (UDFToDouble(key0) + 1.0) (type: double), value (type: string) + outputColumnNames: key, _o__c1, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -98,21 +98,21 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 86.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: '86' (type: string) sort order: + Map-reduce partition columns: '86' (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -131,13 +131,13 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '86' (type: string), 87.0 (type: double), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key0 (type: string), (UDFToDouble(key0) + 1.0) (type: double), value (type: string) + outputColumnNames: key, _o__c1, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/constprog_dp.q.out b/ql/src/test/results/clientpositive/constprog_dp.q.out index 8cf301d..7f72594 100644 --- a/ql/src/test/results/clientpositive/constprog_dp.q.out +++ b/ql/src/test/results/clientpositive/constprog_dp.q.out @@ -33,7 +33,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/correlationoptimizer1.q.out b/ql/src/test/results/clientpositive/correlationoptimizer1.q.out index c5c9d9c..1b64e90 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer1.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer1.q.out @@ -31,51 +31,51 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE @@ -101,17 +101,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -125,21 +125,25 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -179,102 +183,127 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: - Demux Operator - Statistics: Num rows: 263 Data size: 2755 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: sum(_col0), sum(_col1) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: $f0, $f1 + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum($f0), sum($f1) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -329,54 +358,54 @@ STAGE PLANS: Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_1:x + tmp:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_1:x + tmp:x TableScan - alias: x + alias: tmp:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE @@ -393,17 +422,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -417,21 +446,25 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -485,61 +518,60 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: tmp:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE TableScan - alias: y + alias: tmp:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -556,17 +588,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -580,21 +612,25 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -634,103 +670,127 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: x + alias: tmp:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE TableScan - alias: y + alias: tmp:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: - Demux Operator - Statistics: Num rows: 263 Data size: 2755 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: sum(_col0), sum(_col1) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: $f0, $f1 + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum($f0), sum($f1) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -784,45 +844,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -848,17 +908,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -872,21 +932,25 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -926,96 +990,121 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: - Demux Operator - Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Right Outer Join0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: sum(_col0), sum(_col1) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Join Operator + condition map: + Right Outer Join0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: $f0, $f1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum($f0), sum($f1) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1069,50 +1158,54 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1129,17 +1222,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1153,21 +1246,25 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1215,50 +1312,54 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1275,17 +1376,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1299,21 +1400,25 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1368,41 +1473,41 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: key (type: string), value (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: key (type: string), value (type: string) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string), value (type: string) + 1 key (type: string), value (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + expressions: key0 (type: string), value (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -1428,15 +1533,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: string), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1498,41 +1607,41 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: key (type: string), value (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: key (type: string), value (type: string) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string), value (type: string) + 1 key (type: string), value (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + expressions: key0 (type: string), value (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -1558,15 +1667,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: string), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1633,50 +1746,54 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1693,17 +1810,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1717,21 +1834,25 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1771,92 +1892,121 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: - Demux Operator - Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: sum(_col0), sum(_col1) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: $f0, $f1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum($f0), sum($f1) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1910,45 +2060,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -1974,17 +2124,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1998,21 +2148,25 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2060,45 +2214,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -2124,17 +2278,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2148,21 +2302,25 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2218,45 +2376,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -2282,17 +2440,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2306,21 +2464,25 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2368,45 +2530,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -2432,17 +2594,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2456,21 +2618,25 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2520,52 +2686,52 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 + expressions: key0 (type: string), value (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE @@ -2591,17 +2757,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: hash($f0) (type: int), hash($f1) (type: int), hash($f2) (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2) + aggregations: sum($f0), sum($f1), sum($f2) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2615,21 +2781,25 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2677,52 +2847,52 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 + expressions: key0 (type: string), value (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE @@ -2748,17 +2918,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: hash($f0) (type: int), hash($f1) (type: int), hash($f2) (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2) + aggregations: sum($f0), sum($f1), sum($f2) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2772,21 +2942,25 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2836,51 +3010,51 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: tmp:x + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + predicate: (value is not null and key is not null) (type: boolean) + Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: tmp:y + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + predicate: (value is not null and key is not null) (type: boolean) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col2 + 0 key (type: string), value (type: string) + 1 key (type: string), value (type: string) + outputColumnNames: key Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE @@ -2906,17 +3080,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 68 Data size: 724 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 68 Data size: 724 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2930,21 +3104,25 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2992,51 +3170,51 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: tmp:x + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + predicate: (value is not null and key is not null) (type: boolean) + Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: tmp:y + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + predicate: (value is not null and key is not null) (type: boolean) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col2 + 0 key (type: string), value (type: string) + 1 key (type: string), value (type: string) + outputColumnNames: key Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE @@ -3062,17 +3240,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 68 Data size: 724 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 68 Data size: 724 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -3086,21 +3264,25 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/correlationoptimizer10.q.out b/ql/src/test/results/clientpositive/correlationoptimizer10.q.out index 90fb6f4..b3ee9bc 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer10.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer10.q.out @@ -43,56 +43,63 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: xx:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: xx:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -102,15 +109,15 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -123,11 +130,11 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Map-reduce partition columns: $f0 (type: string) + Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: bigint) TableScan alias: yy Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -136,34 +143,33 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -221,42 +227,82 @@ ON xx.key=yy.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: x + alias: xx:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: xx:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) TableScan alias: yy Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -265,71 +311,64 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Demux Operator - Statistics: Num rows: 276 Data size: 2854 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Statistics: Num rows: 257 Data size: 2710 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: $f0, $f1 + Statistics: Num rows: 128 Data size: 1349 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 277 Data size: 2854 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + Statistics: Num rows: 385 Data size: 4059 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator - Statistics: Num rows: 277 Data size: 2854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 385 Data size: 4059 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -417,55 +456,57 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: yy:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 20.0)) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 20.0)) (type: boolean) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: yy:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) > 20.0) and (UDFToDouble(key) < 200.0)) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) > 20.0) and (UDFToDouble(key) < 200.0)) (type: boolean) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 20.0)) (type: boolean) + Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce @@ -474,40 +515,44 @@ STAGE PLANS: alias: xx Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 20.0)) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 20.0)) (type: boolean) + Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 33 Data size: 358 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 33 Data size: 358 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 70 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 70 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -570,104 +615,112 @@ LEFT SEMI JOIN ON xx.key=yy.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: xx - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 20.0)) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: x + alias: yy:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 20.0)) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 20.0)) (type: boolean) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: yy:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) > 20.0) and (UDFToDouble(key) < 200.0)) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) > 20.0) and (UDFToDouble(key) < 200.0)) (type: boolean) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: - Demux Operator - Statistics: Num rows: 57 Data size: 601 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 57 Data size: 601 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 20.0)) (type: boolean) + Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 57 Data size: 601 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: xx + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 20.0)) (type: boolean) + Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + TableScan + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Reduce Operator Tree: + Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 70 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 70 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -745,55 +798,57 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: xx + alias: yy:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 180.0)) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 180.0)) (type: boolean) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE TableScan - alias: xx + alias: yy:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 180.0)) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 180.0)) (type: boolean) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 180.0)) (type: boolean) + Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce @@ -802,40 +857,44 @@ STAGE PLANS: alias: xx Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 180.0)) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 180.0)) (type: boolean) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 33 Data size: 358 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 33 Data size: 358 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -910,104 +969,112 @@ LEFT SEMI JOIN ON xx.key=yy.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: xx + alias: yy:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 180.0)) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 180.0)) (type: boolean) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE TableScan - alias: xx + alias: yy:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 180.0)) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 180.0)) (type: boolean) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 180.0)) (type: boolean) + Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-1 + Map Reduce + Map Operator Tree: TableScan alias: xx Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 180.0)) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) < 200.0) and (UDFToDouble(key) > 180.0)) (type: boolean) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + TableScan + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: - Demux Operator - Statistics: Num rows: 84 Data size: 891 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 84 Data size: 891 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 84 Data size: 891 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/correlationoptimizer11.q.out b/ql/src/test/results/clientpositive/correlationoptimizer11.q.out index 4e65fa5..b46908c 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer11.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer11.q.out @@ -98,18 +98,22 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0 Statistics: Num rows: 55 Data size: 588 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 55 Data size: 588 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 588 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -128,13 +132,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 27 Data size: 288 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 27 Data size: 288 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 27 Data size: 288 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -220,21 +228,29 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false + Mux Operator + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: complete + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -327,18 +343,22 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0 Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -357,13 +377,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -460,21 +484,29 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false + Mux Operator + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: complete + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/correlationoptimizer12.q.out b/ql/src/test/results/clientpositive/correlationoptimizer12.q.out index a541950..c0c89dd 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer12.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer12.q.out @@ -25,7 +25,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: xx:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) @@ -35,35 +35,35 @@ STAGE PLANS: value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col0: string, _col1: string + output shape: key: string, value: string type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col0 - partition by: _col0 + order by: key + partition by: key raw input shape: window functions: window function definition - alias: count_window_0 - arguments: _col1 + alias: $win$_col_0 + arguments: value name: count window function: GenericUDAFCountEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col0 is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), count_window_0 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: key (type: string), $win$_col_0 (type: bigint) + outputColumnNames: key, _o__col6 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -77,40 +77,44 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _o__col6 (type: bigint) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _o__col6 (type: bigint) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, _o__col6, key0, _o__col60 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), _o__col6 (type: bigint), key0 (type: string), _o__col60 (type: bigint) + outputColumnNames: key, _o__col6, key0, _o__col60 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: y + alias: yy:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) @@ -120,35 +124,35 @@ STAGE PLANS: value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col0: string, _col1: string + output shape: key: string, value: string type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col0 - partition by: _col0 + order by: key + partition by: key raw input shape: window functions: window function definition - alias: count_window_0 - arguments: _col1 + alias: $win$_col_1 + arguments: value name: count window function: GenericUDAFCountEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col0 is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), count_window_0 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: key (type: string), $win$_col_1 (type: bigint) + outputColumnNames: key, _o__col6 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/correlationoptimizer13.q.out b/ql/src/test/results/clientpositive/correlationoptimizer13.q.out index d652d87..a7fd8a3 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer13.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer13.q.out @@ -17,9 +17,9 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@tmp POSTHOOK: Lineage: tmp.c1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmp.c2 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: tmp.c2 EXPRESSION [(src)y.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: tmp.c3 SIMPLE [(src)x.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: tmp.c4 SIMPLE [(src)x.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: tmp.c4 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: -- The query in this file have operators with same set of keys -- but having different sorting orders. -- Correlation optimizer currently do not optimize this case. diff --git a/ql/src/test/results/clientpositive/correlationoptimizer14.q.out b/ql/src/test/results/clientpositive/correlationoptimizer14.q.out index bce3100..e0e94f9 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer14.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer14.q.out @@ -95,13 +95,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce @@ -220,13 +224,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce @@ -346,13 +354,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce @@ -521,13 +533,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 @@ -542,13 +558,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -697,13 +717,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce @@ -773,24 +797,24 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: xx:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -804,57 +828,61 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: y + alias: yy:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -951,13 +979,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce @@ -1126,13 +1158,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 @@ -1147,13 +1183,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1302,13 +1342,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce @@ -1319,18 +1363,22 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1338,12 +1386,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -1454,18 +1506,22 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Demux Operator Statistics: Num rows: 263 Data size: 2755 Basic stats: COMPLETE Column stats: NONE @@ -1483,36 +1539,48 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 394 Data size: 4127 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + Mux Operator + Statistics: Num rows: 394 Data size: 4127 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/correlationoptimizer15.q.out b/ql/src/test/results/clientpositive/correlationoptimizer15.q.out index 43ba27d..afe1487 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer15.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer15.q.out @@ -34,56 +34,63 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: xx:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: xx:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -93,15 +100,15 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -114,11 +121,11 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Map-reduce partition columns: $f0 (type: string) + Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: bigint) TableScan alias: yy Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -127,41 +134,45 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), key (type: string) + outputColumnNames: $f0, $f1, key + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string) + key expressions: $f0 (type: string), $f1 (type: bigint), key (type: string) sort order: +++ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -248,42 +259,82 @@ ON xx.key=yy.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: x + alias: xx:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: xx:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) TableScan alias: yy Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -292,66 +343,64 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Demux Operator - Statistics: Num rows: 276 Data size: 2854 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Statistics: Num rows: 257 Data size: 2710 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: $f0, $f1 + Statistics: Num rows: 128 Data size: 1349 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 277 Data size: 2854 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 385 Data size: 4059 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, key + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), key (type: string) + outputColumnNames: $f0, $f1, key + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator - Statistics: Num rows: 277 Data size: 2854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 385 Data size: 4059 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, key Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), key (type: string) + outputColumnNames: $f0, $f1, key Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/correlationoptimizer2.q.out b/ql/src/test/results/clientpositive/correlationoptimizer2.q.out index c1a20c8..a1edc33 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer2.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer2.q.out @@ -36,18 +36,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: tmp:a:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -62,7 +62,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -76,33 +76,33 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, key0, $f10 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: hash(key) (type: int), hash($f1) (type: int), hash(key0) (type: int), hash($f10) (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + aggregations: sum($f0), sum($f1), sum($f2), sum($f3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE @@ -125,32 +125,36 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:b:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE @@ -165,7 +169,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -223,18 +227,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: tmp:a:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -245,18 +249,18 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan - alias: y + alias: tmp:b:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE @@ -273,7 +277,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 262 Data size: 2744 Basic stats: COMPLETE Column stats: NONE @@ -281,16 +285,16 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, key0, $f10 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: hash(key) (type: int), hash($f1) (type: int), hash(key0) (type: int), hash($f10) (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + aggregations: sum($f0), sum($f1), sum($f2), sum($f3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE @@ -304,7 +308,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 262 Data size: 2744 Basic stats: COMPLETE Column stats: NONE @@ -312,16 +316,16 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, key0, $f10 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: hash(key) (type: int), hash($f1) (type: int), hash(key0) (type: int), hash($f10) (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + aggregations: sum($f0), sum($f1), sum($f2), sum($f3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE @@ -344,15 +348,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -407,15 +415,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: tmp:a:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -430,7 +438,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -444,33 +452,33 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, key0, $f10 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: hash(key) (type: int), hash($f1) (type: int), hash(key0) (type: int), hash($f10) (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + aggregations: sum($f0), sum($f1), sum($f2), sum($f3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE @@ -493,29 +501,33 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:b:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -530,7 +542,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -588,15 +600,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: tmp:a:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -607,15 +619,15 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan - alias: y + alias: tmp:b:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -632,7 +644,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE @@ -640,16 +652,16 @@ STAGE PLANS: condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, key0, $f10 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: hash(key) (type: int), hash($f1) (type: int), hash(key0) (type: int), hash($f10) (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + aggregations: sum($f0), sum($f1), sum($f2), sum($f3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE @@ -663,7 +675,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE @@ -671,16 +683,16 @@ STAGE PLANS: condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, key0, $f10 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: hash(key) (type: int), hash($f1) (type: int), hash(key0) (type: int), hash($f10) (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + aggregations: sum($f0), sum($f1), sum($f2), sum($f3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE @@ -703,15 +715,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -766,15 +782,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: tmp:a:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -789,7 +805,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -803,33 +819,33 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) Reduce Operator Tree: Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, key0, $f10 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: hash(key) (type: int), hash($f1) (type: int), hash(key0) (type: int), hash($f10) (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + aggregations: sum($f0), sum($f1), sum($f2), sum($f3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE @@ -852,29 +868,33 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:b:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -889,7 +909,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -947,15 +967,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: tmp:a:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -966,15 +986,15 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan - alias: y + alias: tmp:b:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -991,7 +1011,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE @@ -999,16 +1019,16 @@ STAGE PLANS: condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, key0, $f10 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: hash(key) (type: int), hash($f1) (type: int), hash(key0) (type: int), hash($f10) (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + aggregations: sum($f0), sum($f1), sum($f2), sum($f3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE @@ -1022,7 +1042,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE @@ -1030,16 +1050,16 @@ STAGE PLANS: condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, key0, $f10 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: hash(key) (type: int), hash($f1) (type: int), hash(key0) (type: int), hash($f10) (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + aggregations: sum($f0), sum($f1), sum($f2), sum($f3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE @@ -1062,15 +1082,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1125,15 +1149,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: tmp:a:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1148,7 +1172,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1162,33 +1186,33 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, key0, $f10 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: hash(key) (type: int), hash($f1) (type: int), hash(key0) (type: int), hash($f10) (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + aggregations: sum($f0), sum($f1), sum($f2), sum($f3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE @@ -1211,29 +1235,33 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:b:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -1248,7 +1276,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1306,15 +1334,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: tmp:a:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1325,15 +1353,15 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan - alias: y + alias: tmp:b:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -1350,7 +1378,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE @@ -1358,16 +1386,16 @@ STAGE PLANS: condition map: Outer Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, key0, $f10 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: hash(key) (type: int), hash($f1) (type: int), hash(key0) (type: int), hash($f10) (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + aggregations: sum($f0), sum($f1), sum($f2), sum($f3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE @@ -1381,7 +1409,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE @@ -1389,16 +1417,16 @@ STAGE PLANS: condition map: Outer Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, key0, $f10 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: hash(key) (type: int), hash($f1) (type: int), hash(key0) (type: int), hash($f10) (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + aggregations: sum($f0), sum($f1), sum($f2), sum($f3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE @@ -1421,15 +1449,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1485,14 +1517,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: tmp:a:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1505,7 +1537,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1519,37 +1551,41 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -1566,17 +1602,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1590,34 +1626,38 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-5 Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:b:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -1630,7 +1670,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1699,14 +1739,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: tmp:a:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1716,14 +1756,14 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan - alias: y + alias: tmp:b:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -1738,7 +1778,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE @@ -1746,26 +1786,30 @@ STAGE PLANS: condition map: Outer Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 524 Data size: 5492 Basic stats: COMPLETE Column stats: NONE @@ -1773,22 +1817,26 @@ STAGE PLANS: condition map: Outer Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1805,17 +1853,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash($f0) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1829,21 +1877,25 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1895,99 +1947,109 @@ FROM (SELECT a.key AS key1, a.val AS cnt1, b.key AS key2, b.cnt AS cnt2 ON (a.key = b.key)) tmp POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-5 - Stage-3 depends on stages: Stage-2 - Stage-5 is a root stage - Stage-0 depends on stages: Stage-3 + Stage-4 is a root stage + Stage-1 depends on stages: Stage-4 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 STAGE PLANS: + Stage: Stage-4 + Map Reduce + Map Operator Tree: + TableScan + alias: tmp:b:z + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: key, $f1 + Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:a:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:a:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: + value expressions: value (type: string) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 + Inner Join 1 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: key0, value0, key1, $f1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + expressions: hash(key0) (type: int), hash(value0) (type: int), hash(key1) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + aggregations: sum($f0), sum($f1), sum($f2), sum($f3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE @@ -1998,7 +2060,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-3 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan @@ -2010,54 +2072,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2108,49 +2135,49 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:a:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:a:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: x + alias: tmp:b:z Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE @@ -2163,65 +2190,57 @@ STAGE PLANS: Reduce Operator Tree: Demux Operator Statistics: Num rows: 276 Data size: 2854 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 + Mux Operator + Statistics: Num rows: 690 Data size: 7135 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: key0, value0, key1, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 138 Data size: 1427 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + Select Operator + expressions: hash(key0) (type: int), hash(value0) (type: int), hash(key1) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: sum($f0), sum($f1), sum($f2), sum($f3) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 138 Data size: 1427 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 138 Data size: 1427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 690 Data size: 7135 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 + Inner Join 1 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: key0, value0, key1, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: hash(key0) (type: int), hash(value0) (type: int), hash(key1) (type: int), hash($f1) (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + aggregations: sum($f0), sum($f1), sum($f2), sum($f3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE @@ -2244,15 +2263,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/correlationoptimizer3.q.out b/ql/src/test/results/clientpositive/correlationoptimizer3.q.out index 8510b50..f81a6b1 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer3.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer3.q.out @@ -27,69 +27,76 @@ FROM (SELECT b.key AS key, b.cnt AS cnt, d.value AS value ON b.key = d.key) tmp POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-6 - Stage-3 depends on stages: Stage-2 - Stage-5 is a root stage - Stage-6 depends on stages: Stage-5 - Stage-0 depends on stages: Stage-3 + Stage-4 is a root stage + Stage-5 depends on stages: Stage-4 + Stage-1 depends on stages: Stage-5 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:b:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:b:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Filter Operator + predicate: key0 is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan @@ -97,114 +104,83 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hash(_col0) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) - Reduce Operator Tree: Group By Operator - aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 69 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-5 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:d:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:d:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + TableScan + Reduce Output Operator + key expressions: $f0 (type: string) + sort order: + + Map-reduce partition columns: $f0 (type: string) + Statistics: Num rows: 69 Data size: 732 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: bigint) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 + Inner Join 1 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + 2 $f0 (type: string) + outputColumnNames: key0, value0, $f1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + expressions: hash(key0) (type: int), hash($f1) (type: int), hash(value0) (type: int) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: sum($f0), sum($f1), sum($f2) mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -212,29 +188,31 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-6 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + sort order: + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -276,160 +254,178 @@ FROM (SELECT b.key AS key, b.cnt AS cnt, d.value AS value ON b.key = d.key) tmp POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-4 is a root stage + Stage-1 depends on stages: Stage-4 Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:b:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:b:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key0 is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-1 + Map Reduce + Map Operator Tree: TableScan - alias: y + alias: tmp:d:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:d:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + TableScan + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 526 Data size: 5510 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: hash(_col0) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + Statistics: Num rows: 401 Data size: 4220 Basic stats: COMPLETE Column stats: NONE + Mux Operator + Statistics: Num rows: 1002 Data size: 10544 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 key (type: string) + 1 key (type: string) + 2 $f0 (type: string) + outputColumnNames: key0, value0, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator + Select Operator + expressions: hash(key0) (type: int), hash($f1) (type: int), hash(value0) (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: hash(_col0) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + aggregations: sum($f0), sum($f1), sum($f2) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: $f0, $f1 + Statistics: Num rows: 200 Data size: 2104 Basic stats: COMPLETE Column stats: NONE + Mux Operator + Statistics: Num rows: 1002 Data size: 10544 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 key (type: string) + 1 key (type: string) + 2 $f0 (type: string) + outputColumnNames: key0, value0, $f1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: hash(key0) (type: int), hash($f1) (type: int), hash(value0) (type: int) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: sum($f0), sum($f1), sum($f2) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -443,15 +439,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -495,139 +495,129 @@ FROM (SELECT b.key AS key, b.cnt AS cnt, d.value AS value ON b.key = d.key) tmp POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-9 is a root stage - Stage-2 depends on stages: Stage-9 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 + Stage-7 is a root stage + Stage-1 depends on stages: Stage-7 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-9 + Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_1:x - Fetch Operator - limit: -1 - $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_2:x + tmp:b:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_1:x + tmp:b:x TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_2:x - TableScan - alias: x + alias: tmp:b:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) - Stage: Stage-2 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:d:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: y + alias: tmp:d:x + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + TableScan + alias: tmp:b:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Filter Operator + predicate: key0 is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: Demux Operator - Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 401 Data size: 4220 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 825 Data size: 8763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1002 Data size: 10544 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 + Inner Join 1 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 + 0 key (type: string) + 1 key (type: string) + 2 $f0 (type: string) + outputColumnNames: key0, value0, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: hash(key0) (type: int), hash($f1) (type: int), hash(value0) (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2) + aggregations: sum($f0), sum($f1), sum($f2) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -641,24 +631,26 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 200 Data size: 2104 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 825 Data size: 8763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1002 Data size: 10544 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 + Inner Join 1 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 + 0 key (type: string) + 1 key (type: string) + 2 $f0 (type: string) + outputColumnNames: key0, value0, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: hash(key0) (type: int), hash($f1) (type: int), hash(value0) (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2) + aggregations: sum($f0), sum($f1), sum($f2) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -669,7 +661,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-3 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan @@ -681,15 +673,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -731,69 +727,76 @@ FROM (SELECT d.key AS key, d.cnt AS cnt, b.value as value ON b.key = d.key) tmp POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-6 - Stage-3 depends on stages: Stage-2 - Stage-5 is a root stage - Stage-6 depends on stages: Stage-5 - Stage-0 depends on stages: Stage-3 + Stage-4 is a root stage + Stage-5 depends on stages: Stage-4 + Stage-1 depends on stages: Stage-5 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:d:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:d:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Filter Operator + predicate: key0 is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan @@ -801,114 +804,83 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hash(_col2) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) - Reduce Operator Tree: Group By Operator - aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 69 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-5 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:b:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:b:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + TableScan + Reduce Output Operator + key expressions: $f0 (type: string) + sort order: + + Map-reduce partition columns: $f0 (type: string) + Statistics: Num rows: 69 Data size: 732 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: bigint) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 + Inner Join 1 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + 2 $f0 (type: string) + outputColumnNames: value0, $f0, $f1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + expressions: hash($f0) (type: int), hash($f1) (type: int), hash(value0) (type: int) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: sum($f0), sum($f1), sum($f2) mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -916,29 +888,31 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-6 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + sort order: + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -980,160 +954,178 @@ FROM (SELECT d.key AS key, d.cnt AS cnt, b.value as value ON b.key = d.key) tmp POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-4 is a root stage + Stage-1 depends on stages: Stage-4 Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:d:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:d:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key0 is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-1 + Map Reduce + Map Operator Tree: TableScan - alias: y + alias: tmp:b:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: tmp:b:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + TableScan + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 526 Data size: 5510 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: hash(_col2) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + Statistics: Num rows: 401 Data size: 4220 Basic stats: COMPLETE Column stats: NONE + Mux Operator + Statistics: Num rows: 1002 Data size: 10544 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 key (type: string) + 1 key (type: string) + 2 $f0 (type: string) + outputColumnNames: value0, $f0, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator + Select Operator + expressions: hash($f0) (type: int), hash($f1) (type: int), hash(value0) (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: hash(_col2) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + aggregations: sum($f0), sum($f1), sum($f2) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: $f0, $f1 + Statistics: Num rows: 200 Data size: 2104 Basic stats: COMPLETE Column stats: NONE + Mux Operator + Statistics: Num rows: 1002 Data size: 10544 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 key (type: string) + 1 key (type: string) + 2 $f0 (type: string) + outputColumnNames: value0, $f0, $f1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: hash($f0) (type: int), hash($f1) (type: int), hash(value0) (type: int) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: sum($f0), sum($f1), sum($f2) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1147,15 +1139,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1199,139 +1195,129 @@ FROM (SELECT d.key AS key, d.cnt AS cnt, b.value as value ON b.key = d.key) tmp POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-9 is a root stage - Stage-2 depends on stages: Stage-9 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 + Stage-7 is a root stage + Stage-1 depends on stages: Stage-7 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-9 + Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_1:x - Fetch Operator - limit: -1 - $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_2:x + tmp:d:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_1:x + tmp:d:x TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_2:x - TableScan - alias: x + alias: tmp:d:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) - Stage: Stage-2 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:b:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: y + alias: tmp:b:x + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + TableScan + alias: tmp:d:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Filter Operator + predicate: key0 is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: Demux Operator - Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 401 Data size: 4220 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 825 Data size: 8763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1002 Data size: 10544 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 + Inner Join 1 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + 2 $f0 (type: string) + outputColumnNames: value0, $f0, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: hash(_col2) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: hash($f0) (type: int), hash($f1) (type: int), hash(value0) (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2) + aggregations: sum($f0), sum($f1), sum($f2) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -1345,24 +1331,26 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 200 Data size: 2104 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 825 Data size: 8763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1002 Data size: 10544 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 + Inner Join 1 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + 2 $f0 (type: string) + outputColumnNames: value0, $f0, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: hash(_col2) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: hash($f0) (type: int), hash($f1) (type: int), hash(value0) (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1), sum(_col2) + aggregations: sum($f0), sum($f1), sum($f2) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -1373,7 +1361,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-3 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan @@ -1385,15 +1373,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/correlationoptimizer4.q.out b/ql/src/test/results/clientpositive/correlationoptimizer4.q.out index 95ed861..5907d5d 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer4.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer4.q.out @@ -120,18 +120,22 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col5 Statistics: Num rows: 8 Data size: 37 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col5 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col5 (type: int) + outputColumnNames: _col5 Statistics: Num rows: 8 Data size: 37 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count(1) + keys: _col5 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 8 Data size: 37 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -150,17 +154,21 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 4 Data size: 18 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) - mode: hash + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 4 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -176,13 +184,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -276,25 +288,33 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col5 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator + Select Operator + expressions: _col5 (type: int) + outputColumnNames: _col5 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col5 (type: int) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Mux Operator + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) - mode: hash + aggregations: count(1) + keys: _col5 (type: int) + mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -310,13 +330,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -418,18 +442,22 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col5 Statistics: Num rows: 8 Data size: 37 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col5 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col5 (type: int) + outputColumnNames: _col5 Statistics: Num rows: 8 Data size: 37 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + Group By Operator + aggregations: count(1) + keys: _col5 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 37 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 8 Data size: 37 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -439,17 +467,21 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 4 Data size: 18 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) - mode: hash + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 4 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -465,13 +497,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -559,18 +595,22 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count(1) + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -589,17 +629,21 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) - mode: hash + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -615,13 +659,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -706,25 +754,33 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Mux Operator + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) - mode: hash + aggregations: count(1) + keys: _col0 (type: int) + mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -740,13 +796,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -836,18 +896,22 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col5 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col5 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col5 (type: int) + outputColumnNames: _col5 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count(1) + keys: _col5 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -866,17 +930,21 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) - mode: hash + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -892,13 +960,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -986,18 +1058,22 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col10 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col10 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col10 (type: int) + outputColumnNames: _col10 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count(1) + keys: _col10 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1016,17 +1092,21 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) - mode: hash + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -1042,13 +1122,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1133,25 +1217,33 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col10 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator + Select Operator + expressions: _col10 (type: int) + outputColumnNames: _col10 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col10 (type: int) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Mux Operator + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) - mode: hash + aggregations: count(1) + keys: _col10 (type: int) + mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1167,13 +1259,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1263,18 +1359,22 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col5 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col5 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col5 (type: int) + outputColumnNames: _col5 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count(1) + keys: _col5 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1293,17 +1393,21 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) - mode: hash + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -1319,13 +1423,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1413,18 +1521,22 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col5 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col5 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col5 (type: int) + outputColumnNames: _col5 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count(1) + keys: _col5 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1443,17 +1555,21 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) - mode: hash + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -1469,13 +1585,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1559,18 +1679,22 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col5 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col5 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col5 (type: int) + outputColumnNames: _col5 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count(1) + keys: _col5 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1589,17 +1713,21 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)) - mode: hash + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -1615,13 +1743,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/correlationoptimizer5.q.out b/ql/src/test/results/clientpositive/correlationoptimizer5.q.out index 7f2e19f..9f813d8 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer5.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer5.q.out @@ -150,12 +150,16 @@ STAGE PLANS: 1 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -365,28 +369,32 @@ STAGE PLANS: 1 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col3 + Mux Operator Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col3 (type: string) - outputColumnNames: _col0, _col1 + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: int), _col3 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest_co2 + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_co2 Join Operator condition map: Inner Join 0 to 1 @@ -534,12 +542,16 @@ STAGE PLANS: 1 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/correlationoptimizer6.q.out b/ql/src/test/results/clientpositive/correlationoptimizer6.q.out index 6b003d5..2f6b4e1 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer6.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer6.q.out @@ -37,56 +37,60 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: xx:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: xx:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -103,7 +107,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -117,89 +121,97 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f0, $f1, $f00, $f10 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), $f00 (type: string), $f10 (type: bigint) + outputColumnNames: $f0, $f1, $f00, $f10 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-5 Map Reduce Map Operator Tree: TableScan - alias: x + alias: yy:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: yy:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-6 Map Reduce @@ -216,7 +228,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -284,141 +296,203 @@ ON xx.key=yy.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-1, Stage-4 + Stage-4 is a root stage + Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: x + alias: xx:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: xx:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + TableScan + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reduce Operator Tree: + Demux Operator + Statistics: Num rows: 289 Data size: 3029 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: $f0, $f1 + Statistics: Num rows: 144 Data size: 1509 Basic stats: COMPLETE Column stats: NONE + Mux Operator + Statistics: Num rows: 288 Data size: 3018 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f0, $f1, $f00, $f10 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), $f00 (type: string), $f10 (type: bigint) + outputColumnNames: $f0, $f1, $f00, $f10 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: $f0, $f1 + Statistics: Num rows: 144 Data size: 1509 Basic stats: COMPLETE Column stats: NONE + Mux Operator + Statistics: Num rows: 288 Data size: 3018 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f0, $f1, $f00, $f10 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), $f00 (type: string), $f10 (type: bigint) + outputColumnNames: $f0, $f1, $f00, $f10 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-4 + Map Reduce + Map Operator Tree: TableScan - alias: x + alias: yy:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: yy:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: - Demux Operator - Statistics: Num rows: 526 Data size: 5510 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -488,107 +562,115 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_0:x + xx:x Fetch Operator limit: -1 - $hdt$_1:$hdt$_1:$hdt$_1:x + yy:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_0:x + xx:x TableScan - alias: x + alias: xx:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - $hdt$_1:$hdt$_1:$hdt$_1:x + 0 key (type: string) + 1 key (type: string) + yy:x TableScan - alias: x + alias: yy:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: x + alias: xx:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) TableScan - alias: x + alias: yy:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -598,7 +680,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 144 Data size: 1509 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 288 Data size: 3018 Basic stats: COMPLETE Column stats: NONE @@ -606,22 +688,26 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f0, $f1, $f00, $f10 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), $f00 (type: string), $f10 (type: bigint) + outputColumnNames: $f0, $f1, $f00, $f10 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 144 Data size: 1509 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 288 Data size: 3018 Basic stats: COMPLETE Column stats: NONE @@ -629,17 +715,21 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f0, $f1, $f00, $f10 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), $f00 (type: string), $f10 (type: bigint) + outputColumnNames: $f0, $f1, $f00, $f10 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -712,18 +802,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: yy:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -738,7 +828,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -758,36 +848,40 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 key (type: string) + 1 $f0 (type: string) + outputColumnNames: key, $f0, $f1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f0 (type: string), $f1 (type: bigint) + outputColumnNames: key, $f0, $f1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -858,26 +952,26 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: yy:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -896,22 +990,26 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 key (type: string) + 1 $f0 (type: string) + outputColumnNames: key, $f0, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f0 (type: string), $f1 (type: bigint) + outputColumnNames: key, $f0, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 394 Data size: 4127 Basic stats: COMPLETE Column stats: NONE @@ -919,17 +1017,21 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 key (type: string) + 1 $f0 (type: string) + outputColumnNames: key, $f0, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f0 (type: string), $f1 (type: bigint) + outputColumnNames: key, $f0, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1001,56 +1103,63 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: yy:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: yy:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -1060,15 +1169,15 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 69 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1087,36 +1196,40 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Map-reduce partition columns: $f0 (type: string) + Statistics: Num rows: 69 Data size: 732 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: bigint) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 key (type: string) + 1 $f0 (type: string) + outputColumnNames: key, $f0, $f1 + Statistics: Num rows: 75 Data size: 805 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), $f0 (type: string), $f1 (type: bigint) + outputColumnNames: key, $f0, $f1 + Statistics: Num rows: 75 Data size: 805 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 75 Data size: 805 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1172,111 +1285,149 @@ JOIN ON xx.key=yy.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: xx - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: yy:x + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: yy:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-1 + Map Reduce + Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: xx + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + TableScan + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 513 Data size: 5411 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 151 Data size: 1564 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 514 Data size: 5411 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 226 Data size: 2340 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 key (type: string) + 1 $f0 (type: string) + outputColumnNames: key, $f0, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f0 (type: string), $f1 (type: bigint) + outputColumnNames: key, $f0, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: $f0, $f1 + Statistics: Num rows: 75 Data size: 776 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 514 Data size: 5411 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 226 Data size: 2340 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 $f0 (type: string) + outputColumnNames: key, $f0, $f1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: string), $f0 (type: string), $f1 (type: bigint) + outputColumnNames: key, $f0, $f1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1348,56 +1499,63 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: xx:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: xx:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1407,15 +1565,15 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1428,11 +1586,11 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Map-reduce partition columns: $f0 (type: string) + Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: bigint) TableScan alias: yy Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1441,29 +1599,33 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), key (type: string) + outputColumnNames: $f0, $f1, key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1542,42 +1704,82 @@ ON xx.key=yy.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: x + alias: xx:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: xx:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) TableScan alias: yy Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1586,66 +1788,64 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Demux Operator - Statistics: Num rows: 276 Data size: 2854 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Statistics: Num rows: 257 Data size: 2710 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: $f0, $f1 + Statistics: Num rows: 128 Data size: 1349 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 277 Data size: 2854 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 385 Data size: 4059 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, key + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), key (type: string) + outputColumnNames: $f0, $f1, key + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator - Statistics: Num rows: 277 Data size: 2854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 385 Data size: 4059 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, key Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), key (type: string) + outputColumnNames: $f0, $f1, key Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1741,56 +1941,63 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: zz + alias: yy:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: zz + alias: yy:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -1800,15 +2007,15 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 69 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1827,12 +2034,12 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan alias: xx @@ -1842,34 +2049,34 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Map-reduce partition columns: $f0 (type: string) + Statistics: Num rows: 69 Data size: 732 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: bigint) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + 2 $f0 (type: string) + outputColumnNames: key0, $f0, $f1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col2 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: key0 (type: string), $f0 (type: string), $f1 (type: bigint) + outputColumnNames: key, key1, cnt Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1965,43 +2172,76 @@ JOIN ON zz.key=yy.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-3 is a root stage + Stage-1 depends on stages: Stage-3 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: zz + alias: yy:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: xx - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: yy:y + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-1 + Map Reduce + Map Operator Tree: TableScan alias: zz Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -2010,46 +2250,53 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: zz - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: xx + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + TableScan + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 763 Data size: 8067 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 401 Data size: 4220 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 1527 Data size: 16134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1002 Data size: 10544 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + 2 $f0 (type: string) + outputColumnNames: key0, $f0, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col2 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: key0 (type: string), $f0 (type: string), $f1 (type: bigint) + outputColumnNames: key, key1, cnt Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator compressed: false @@ -2058,45 +2305,35 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: $f0, $f1 + Statistics: Num rows: 200 Data size: 2104 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 1527 Data size: 16134 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 0 to 2 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 + Statistics: Num rows: 1002 Data size: 10544 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 0 to 2 + keys: + 0 key (type: string) + 1 key (type: string) + 2 $f0 (type: string) + outputColumnNames: key0, $f0, $f1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key0 (type: string), $f0 (type: string), $f1 (type: bigint) + outputColumnNames: key, key1, cnt + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2194,56 +2431,63 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: yy:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: yy:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Filter Operator + predicate: key0 is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -2253,15 +2497,15 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 69 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2274,25 +2518,25 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Map-reduce partition columns: $f0 (type: string) + Statistics: Num rows: 69 Data size: 732 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: bigint) TableScan - alias: x + alias: zz Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan alias: xx @@ -2302,12 +2546,12 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator @@ -2315,14 +2559,14 @@ STAGE PLANS: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 + 0 $f0 (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: $f0, $f1, key0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col3 (type: string), _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: key0 (type: string), $f0 (type: string), $f1 (type: bigint) + outputColumnNames: key, key1, cnt Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2413,56 +2657,96 @@ ON yy.key=zz.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: x + alias: yy:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: yy:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key0 is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) TableScan - alias: x + alias: zz Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan alias: xx @@ -2472,70 +2756,60 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Demux Operator - Statistics: Num rows: 763 Data size: 8067 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Statistics: Num rows: 401 Data size: 4220 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: $f0, $f1 + Statistics: Num rows: 200 Data size: 2104 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 1527 Data size: 16134 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 0 to 2 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 1002 Data size: 10544 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 0 to 2 + keys: + 0 $f0 (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: $f0, $f1, key0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key0 (type: string), $f0 (type: string), $f1 (type: bigint) + outputColumnNames: key, key1, cnt + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col3 (type: string), _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator - Statistics: Num rows: 1527 Data size: 16134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1002 Data size: 10544 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 + 0 $f0 (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: $f0, $f1, key0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col3 (type: string), _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: key0 (type: string), $f0 (type: string), $f1 (type: bigint) + outputColumnNames: key, key1, cnt Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator compressed: false @@ -2645,18 +2919,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: tmp:xx:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -2671,7 +2945,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2685,43 +2959,46 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, $f10 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col1), sum(_col2) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 69 Data size: 735 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), $f1 (type: bigint), $f10 (type: bigint) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 69 Data size: 735 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum($f1), sum($f2) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 69 Data size: 735 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -2731,15 +3008,15 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 69 Data size: 735 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 68 Data size: 724 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 34 Data size: 362 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2752,39 +3029,39 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 68 Data size: 724 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint), _col2 (type: bigint) + Map-reduce partition columns: $f0 (type: string) + Statistics: Num rows: 34 Data size: 362 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: bigint), $f2 (type: bigint) TableScan - alias: x + alias: z Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col4 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, $f2, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: bigint), _col0 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: $f0 (type: string), $f1 (type: bigint), $f2 (type: bigint), $f0 (type: string), value (type: string) + outputColumnNames: $f0, $f1, $f2, key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2798,18 +3075,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y + alias: tmp:yy:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE @@ -2824,7 +3101,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2918,25 +3195,26 @@ JOIN src z ON tmp.key=z.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: x + alias: tmp:xx:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -2947,18 +3225,18 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan - alias: y + alias: tmp:yy:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE @@ -2968,136 +3246,149 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) - TableScan - alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 513 Data size: 5411 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 263 Data size: 2755 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 256 Data size: 2700 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, $f1 + Statistics: Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 512 Data size: 5400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 2744 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, $f10 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + Filter Operator + predicate: key is not null (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator + Select Operator + expressions: key (type: string), $f1 (type: bigint), $f10 (type: bigint) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(_col1), sum(_col2) - keys: _col0 (type: string) - mode: complete + aggregations: sum($f1), sum($f2) + keys: $f0 (type: string) + mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 514 Data size: 5411 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: bigint), _col0 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 256 Data size: 2700 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, $f1 + Statistics: Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 512 Data size: 5400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 2744 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, $f10 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + Filter Operator + predicate: key is not null (type: boolean) Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator + Select Operator + expressions: key (type: string), $f1 (type: bigint), $f10 (type: bigint) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: sum(_col1), sum(_col2) - keys: _col0 (type: string) - mode: complete + aggregations: sum($f1), sum($f2) + keys: $f0 (type: string) + mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 514 Data size: 5411 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: bigint), _col0 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: bigint), _col2 (type: bigint) + TableScan + alias: z + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reduce Operator Tree: + Demux Operator + Statistics: Num rows: 251 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 125 Data size: 1322 Basic stats: COMPLETE Column stats: NONE + Mux Operator + Statistics: Num rows: 376 Data size: 3978 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, $f2, value + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), $f2 (type: bigint), $f0 (type: string), value (type: string) + outputColumnNames: $f0, $f1, $f2, key, value + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator - Statistics: Num rows: 514 Data size: 5411 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 376 Data size: 3978 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col4 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, $f2, value Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: bigint), _col0 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: $f0 (type: string), $f1 (type: bigint), $f2 (type: bigint), $f0 (type: string), value (type: string) + outputColumnNames: $f0, $f1, $f2, key, value Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator compressed: false @@ -3210,56 +3501,60 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: xx:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x + alias: xx:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -3276,7 +3571,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -3290,46 +3585,50 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 7 Data size: 54 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: bigint) + value expressions: $f1 (type: string), $f2 (type: bigint) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f0, $f1, $f00, $f10, $f2 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), $f00 (type: string), $f10 (type: string), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f00, $f10, $f2 + Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: string), _col4 (type: bigint) + key expressions: $f0 (type: string), $f1 (type: bigint), $f00 (type: string), $f10 (type: string), $f2 (type: bigint) sort order: +++++ Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: $f0, $f1, $f00, $f10, $f2 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -3343,57 +3642,61 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: yy:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: x + alias: yy:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: key (type: string), value (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-7 Map Reduce @@ -3410,7 +3713,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -3477,69 +3780,202 @@ JOIN ON xx.key=yy.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-3 is a root stage - Stage-4 depends on stages: Stage-3 - Stage-1 depends on stages: Stage-4 - Stage-0 depends on stages: Stage-1 + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1, Stage-5 + Stage-4 is a root stage + Stage-5 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-3 + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: xx:x + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + TableScan + alias: xx:y + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + TableScan + Reduce Output Operator + key expressions: $f0 (type: string) + sort order: + + Map-reduce partition columns: $f0 (type: string) + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: string), $f2 (type: bigint) + Reduce Operator Tree: + Demux Operator + Statistics: Num rows: 151 Data size: 1563 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: $f0, $f1 + Statistics: Num rows: 75 Data size: 776 Basic stats: COMPLETE Column stats: NONE + Mux Operator + Statistics: Num rows: 226 Data size: 2339 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f0, $f1, $f00, $f10, $f2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), $f00 (type: string), $f10 (type: string), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f00, $f10, $f2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Mux Operator + Statistics: Num rows: 226 Data size: 2339 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f0, $f1, $f00, $f10, $f2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), $f00 (type: string), $f10 (type: string), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f00, $f10, $f2 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: x + alias: yy:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: x + alias: yy:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: key (type: string), value (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-4 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan @@ -3554,7 +3990,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -3563,100 +3999,6 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: bigint) - Reduce Operator Tree: - Demux Operator - Statistics: Num rows: 163 Data size: 1653 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 164 Data size: 1653 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Mux Operator - Statistics: Num rows: 164 Data size: 1653 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-0 Fetch Operator limit: -1 @@ -3725,59 +4067,63 @@ STAGE PLANS: Stage: Stage-10 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:$hdt$_1:$hdt$_1:x + yy:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:$hdt$_1:$hdt$_1:x + yy:x TableScan - alias: x + alias: yy:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-5 Map Reduce Map Operator Tree: TableScan - alias: x + alias: yy:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: key (type: string), value (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Group By Operator + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -3785,7 +4131,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -3797,66 +4143,70 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_0:x + xx:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_0:x + xx:x TableScan - alias: x + alias: xx:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: bigint) + value expressions: $f1 (type: string), $f2 (type: bigint) TableScan - alias: x + alias: xx:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -3866,7 +4216,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 75 Data size: 776 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 226 Data size: 2339 Basic stats: COMPLETE Column stats: NONE @@ -3874,34 +4224,42 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f0, $f1, $f00, $f10, $f2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), $f00 (type: string), $f10 (type: string), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f00, $f10, $f2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator Statistics: Num rows: 226 Data size: 2339 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f0, $f1, $f00, $f10, $f2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), $f00 (type: string), $f10 (type: string), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f00, $f10, $f2 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/correlationoptimizer7.q.out b/ql/src/test/results/clientpositive/correlationoptimizer7.q.out index 6514c4a..ac773a7 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer7.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer7.q.out @@ -29,59 +29,66 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_1:y + xx:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_1:y + xx:y TableScan - alias: y + alias: xx:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: x + alias: xx:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -89,8 +96,8 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 69 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -101,25 +108,25 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:y + yy Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:y + yy TableScan - alias: y + alias: yy Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 $f0 (type: string) + 1 key (type: string) Stage: Stage-6 Map Reduce @@ -129,17 +136,21 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, key, value + Statistics: Num rows: 75 Data size: 805 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), key (type: string), value (type: string) + outputColumnNames: $f0, $f1, key, value + Statistics: Num rows: 75 Data size: 805 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 75 Data size: 805 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -209,120 +220,135 @@ STAGE PLANS: Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_1:y + xx:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_1:y + xx:y TableScan - alias: y + alias: xx:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: y + alias: yy Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: x + alias: xx:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: Demux Operator - Statistics: Num rows: 288 Data size: 3020 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 151 Data size: 1564 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 144 Data size: 1510 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 75 Data size: 776 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 432 Data size: 4530 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 226 Data size: 2340 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, key, value Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), key (type: string), value (type: string) + outputColumnNames: $f0, $f1, key, value Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator - Statistics: Num rows: 432 Data size: 4530 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 226 Data size: 2340 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, key, value Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), key (type: string), value (type: string) + outputColumnNames: $f0, $f1, key, value Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -404,59 +430,66 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_1:y + xx:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_1:y + xx:y TableScan - alias: y + alias: xx:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: x + alias: xx:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -464,8 +497,8 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 69 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -476,25 +509,25 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:y + yy Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:y + yy TableScan - alias: y + alias: yy Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 $f0 (type: string) + 1 key (type: string) Stage: Stage-6 Map Reduce @@ -504,17 +537,21 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, key, value + Statistics: Num rows: 75 Data size: 805 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), key (type: string), value (type: string) + outputColumnNames: $f0, $f1, key, value + Statistics: Num rows: 75 Data size: 805 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 75 Data size: 805 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -584,120 +621,135 @@ STAGE PLANS: Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_1:y + xx:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_1:y + xx:y TableScan - alias: y + alias: xx:y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: y + alias: yy Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: x + alias: xx:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: Demux Operator - Statistics: Num rows: 288 Data size: 3020 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 151 Data size: 1564 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 144 Data size: 1510 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 75 Data size: 776 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 432 Data size: 4530 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 226 Data size: 2340 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, key, value Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), key (type: string), value (type: string) + outputColumnNames: $f0, $f1, key, value Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator - Statistics: Num rows: 432 Data size: 4530 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 226 Data size: 2340 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, key, value Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), key (type: string), value (type: string) + outputColumnNames: $f0, $f1, key, value Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/correlationoptimizer8.q.out b/ql/src/test/results/clientpositive/correlationoptimizer8.q.out index 97b79e2..977e63b 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer8.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer8.q.out @@ -43,34 +43,34 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: null-subquery1:subq1-subquery1:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(key) < 20.0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) < 20.0) and ((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0))) (type: boolean) + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -83,54 +83,54 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Map-reduce partition columns: $f0 (type: string) + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: bigint) TableScan Union - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Map-reduce partition columns: $f0 (type: string) + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: bigint) TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0)) and key is not null) (type: boolean) + predicate: (key is not null and ((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0))) (type: boolean) Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f1, key, value + Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col3 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string), $f1 (type: bigint) + outputColumnNames: key, value, cnt + Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -140,40 +140,44 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: null-subquery2:subq1-subquery2:x1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(key) > 100.0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) > 100.0) and ((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0))) (type: boolean) + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -243,89 +247,89 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: null-subquery1:subq1-subquery1:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(key) < 20.0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) < 20.0) and ((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0))) (type: boolean) + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan - alias: x + alias: null-subquery2:subq1-subquery2:x1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(key) > 100.0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) > 100.0) and ((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0))) (type: boolean) + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0)) and key is not null) (type: boolean) + predicate: (key is not null and ((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0))) (type: boolean) Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 340 Data size: 3587 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 228 Data size: 2397 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 170 Data size: 1793 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 114 Data size: 1198 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 340 Data size: 3586 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 228 Data size: 2396 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 680 Data size: 7173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 456 Data size: 4793 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f1, key, value Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col3 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), value (type: string), $f1 (type: bigint) + outputColumnNames: key, value, cnt Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator compressed: false @@ -338,44 +342,48 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 170 Data size: 1793 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 340 Data size: 3586 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 680 Data size: 7173 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col2 (type: string), _col3 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1 + Statistics: Num rows: 114 Data size: 1198 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 114 Data size: 1198 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 228 Data size: 2396 Basic stats: COMPLETE Column stats: NONE + Mux Operator + Statistics: Num rows: 456 Data size: 4793 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f1, key, value Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), $f1 (type: bigint) + outputColumnNames: key, value, cnt Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator - Statistics: Num rows: 680 Data size: 7173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 456 Data size: 4793 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f1, key, value Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col3 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), value (type: string), $f1 (type: bigint) + outputColumnNames: key, value, cnt Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE File Output Operator compressed: false @@ -467,18 +475,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: null-subquery1:subq1-subquery1:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 20.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -493,7 +501,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -509,66 +517,70 @@ STAGE PLANS: Union Statistics: Num rows: 87 Data size: 911 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 87 Data size: 911 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) TableScan Union Statistics: Num rows: 87 Data size: 911 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 87 Data size: 911 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) TableScan - alias: x1 + alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, key, value Statistics: Num rows: 95 Data size: 1002 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), key (type: string), value (type: string) + outputColumnNames: $f0, $f1, key, value Statistics: Num rows: 95 Data size: 1002 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 95 Data size: 1002 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: x1 + alias: null-subquery2:subq1-subquery2:x1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) > 100.0) (type: boolean) Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 + expressions: value (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE @@ -583,14 +595,18 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 4 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 4 Data size: 30 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -680,18 +696,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: null-subquery1:subq1-subquery1:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 20.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -702,18 +718,18 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan - alias: x1 + alias: null-subquery2:subq1-subquery2:x1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) > 100.0) (type: boolean) Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 + expressions: value (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE @@ -724,18 +740,18 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan - alias: x1 + alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Demux Operator Statistics: Num rows: 199 Data size: 2015 Basic stats: COMPLETE Column stats: NONE @@ -743,7 +759,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 99 Data size: 1002 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 198 Data size: 2004 Basic stats: COMPLETE Column stats: NONE @@ -753,59 +769,75 @@ STAGE PLANS: condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, key, value Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), key (type: string), value (type: string) + outputColumnNames: $f0, $f1, key, value Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 99 Data size: 1002 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 198 Data size: 2004 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 397 Data size: 4019 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 99 Data size: 1002 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 198 Data size: 2004 Basic stats: COMPLETE Column stats: NONE + Mux Operator + Statistics: Num rows: 397 Data size: 4019 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, key, value Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), key (type: string), value (type: string) + outputColumnNames: $f0, $f1, key, value + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator Statistics: Num rows: 397 Data size: 4019 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f0, $f1, key, value Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), key (type: string), value (type: string) + outputColumnNames: $f0, $f1, key, value Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -903,34 +935,34 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: null-subquery1:subq1-subquery1:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(key) < 20.0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) < 20.0) and ((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0))) (type: boolean) + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -943,54 +975,54 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Map-reduce partition columns: $f0 (type: string) + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: bigint) TableScan Union - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Map-reduce partition columns: $f0 (type: string) + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: bigint) TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0)) and key is not null) (type: boolean) + predicate: (key is not null and ((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0))) (type: boolean) Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f1, key, value + Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col3 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string), $f1 (type: bigint) + outputColumnNames: key, value, cnt + Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1000,38 +1032,38 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: null-subquery2:subq1-subquery2:x1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(key) > 100.0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) > 100.0) and ((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0))) (type: boolean) + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + expressions: $f0 (type: string), $f2 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1081,18 +1113,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: null-subquery1:subq1-subquery1:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 20.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -1107,11 +1139,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToLong(UDFToInteger(_col0)) (type: bigint), _col1 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: UDFToLong(UDFToInteger($f0)) (type: bigint), $f1 (type: bigint) + outputColumnNames: key, value Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1127,66 +1159,70 @@ STAGE PLANS: Union Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) + key expressions: UDFToDouble(key) (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Map-reduce partition columns: UDFToDouble(key) (type: double) Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) + value expressions: key (type: bigint), value (type: bigint) TableScan Union Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) + key expressions: UDFToDouble(key) (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Map-reduce partition columns: UDFToDouble(key) (type: double) Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) + value expressions: key (type: bigint), value (type: bigint) TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) + key expressions: UDFToDouble(key) (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Map-reduce partition columns: UDFToDouble(key) (type: double) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) + value expressions: key (type: string), value (type: string) Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 keys: - 0 UDFToDouble(_col0) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 UDFToDouble(key) (type: double) + 1 UDFToDouble(key) (type: double) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: bigint), value (type: bigint), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: x + alias: null-subquery2:subq1-subquery2:x1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) > 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -1201,11 +1237,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint), UDFToLong(UDFToInteger(_col0)) (type: bigint) - outputColumnNames: _col0, _col1 + expressions: $f1 (type: bigint), UDFToLong(UDFToInteger($f0)) (type: bigint) + outputColumnNames: key, value Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/correlationoptimizer9.q.out b/ql/src/test/results/clientpositive/correlationoptimizer9.q.out index e00860d..afe1ca7 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer9.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer9.q.out @@ -21,9 +21,9 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@tmp POSTHOOK: Lineage: tmp.c1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmp.c2 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: tmp.c2 EXPRESSION [(src)y.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: tmp.c3 SIMPLE [(src)x.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: tmp.c4 SIMPLE [(src)x.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: tmp.c4 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: EXPLAIN SELECT xx.key, yy.key, xx.cnt, yy.cnt FROM @@ -56,18 +56,22 @@ STAGE PLANS: Filter Operator predicate: (c1 < 120) (type: boolean) Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: c1 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: c1 (type: int) + outputColumnNames: c1 Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + Group By Operator + aggregations: count(1) + keys: c1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -75,12 +79,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 171 Data size: 3819 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 171 Data size: 3819 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -129,18 +137,22 @@ STAGE PLANS: Filter Operator predicate: (c2 > 100) (type: boolean) Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: c2 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: c2 (type: int) + outputColumnNames: c2 Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + Group By Operator + aggregations: count(1) + keys: c2 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -148,12 +160,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 171 Data size: 3819 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 171 Data size: 3819 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -220,36 +236,44 @@ STAGE PLANS: Filter Operator predicate: (c1 < 120) (type: boolean) Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: c1 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: c1 (type: int) + outputColumnNames: c1 Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + Group By Operator + aggregations: count(1) + keys: c1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) TableScan alias: x1 Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (c2 > 100) (type: boolean) Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: c2 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: c2 (type: int) + outputColumnNames: c2 Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + Group By Operator + aggregations: count(1) + keys: c2 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Demux Operator Statistics: Num rows: 684 Data size: 15278 Basic stats: COMPLETE Column stats: NONE @@ -259,54 +283,62 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 684 Data size: 15278 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col2 (type: int), _col1 (type: bigint), _col3 (type: bigint) + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE + Mux Operator + Statistics: Num rows: 684 Data size: 15278 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: int), _col2 (type: int), _col1 (type: bigint), _col3 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 684 Data size: 15278 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col2 (type: int), _col1 (type: bigint), _col3 (type: bigint) + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE + Mux Operator + Statistics: Num rows: 684 Data size: 15278 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: int), _col2 (type: int), _col1 (type: bigint), _col3 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -373,18 +405,22 @@ STAGE PLANS: Filter Operator predicate: ((c1 < 120) and c3 is not null) (type: boolean) Statistics: Num rows: 171 Data size: 3819 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: c1 (type: int), c3 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: c1 (type: int), c3 (type: string) + outputColumnNames: c1, c3 Statistics: Num rows: 171 Data size: 3819 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Group By Operator + aggregations: count(1) + keys: c1 (type: int), c3 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 171 Data size: 3819 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Statistics: Num rows: 171 Data size: 3819 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -392,12 +428,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 85 Data size: 1898 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 85 Data size: 1898 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -469,12 +509,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 43 Data size: 960 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 43 Data size: 960 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -539,18 +583,22 @@ STAGE PLANS: Filter Operator predicate: ((c1 < 120) and c3 is not null) (type: boolean) Statistics: Num rows: 171 Data size: 3819 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: c1 (type: int), c3 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: c1 (type: int), c3 (type: string) + outputColumnNames: c1, c3 Statistics: Num rows: 171 Data size: 3819 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Group By Operator + aggregations: count(1) + keys: c1 (type: int), c3 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 171 Data size: 3819 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Statistics: Num rows: 171 Data size: 3819 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) TableScan alias: x1 Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE @@ -582,54 +630,62 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 128 Data size: 2858 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 256 Data size: 5716 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int), _col1 (type: string) - 1 _col0 (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string), _col2 (type: bigint), _col5 (type: bigint) + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 128 Data size: 2858 Basic stats: COMPLETE Column stats: NONE + Mux Operator + Statistics: Num rows: 256 Data size: 5716 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int), _col1 (type: string) + 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string), _col2 (type: bigint), _col5 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 128 Data size: 2858 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 256 Data size: 5716 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int), _col1 (type: string) - 1 _col0 (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string), _col2 (type: bigint), _col5 (type: bigint) + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 128 Data size: 2858 Basic stats: COMPLETE Column stats: NONE + Mux Operator + Statistics: Num rows: 256 Data size: 5716 Basic stats: COMPLETE Column stats: NONE + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int), _col1 (type: string) + 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string), _col2 (type: bigint), _col5 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/count.q.out b/ql/src/test/results/clientpositive/count.q.out index e8d0cb3..111f590 100644 --- a/ql/src/test/results/clientpositive/count.q.out +++ b/ql/src/test/results/clientpositive/count.q.out @@ -48,11 +48,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), count(DISTINCT _col2), sum(_col3) - keys: _col0 (type: int), _col1 (type: int), _col2 (type: int) + aggregations: count(DISTINCT b), count(DISTINCT c), sum(d) + keys: a (type: int), b (type: int), c (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE @@ -67,15 +67,19 @@ STAGE PLANS: aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0), sum(VALUE._col2) keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, $f1, $f2, $f3 Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: a (type: int), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint) + outputColumnNames: a, $f1, $f2, $f3 Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -111,12 +115,12 @@ STAGE PLANS: alias: abcd Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 + expressions: 1 (type: int), a (type: int), b (type: int), c (type: int), d (type: int) + outputColumnNames: $f0, $f1, $f2, $f3, $f4 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), count(), count(_col1), count(_col2), count(_col3), count(_col4), count(DISTINCT _col1), count(DISTINCT _col2), count(DISTINCT _col3), count(DISTINCT _col4), count(DISTINCT _col1, _col2), count(DISTINCT _col2, _col3), count(DISTINCT _col3, _col4), count(DISTINCT _col1, _col4), count(DISTINCT _col1, _col3), count(DISTINCT _col2, _col4), count(DISTINCT _col1, _col2, _col3), count(DISTINCT _col2, _col3, _col4), count(DISTINCT _col1, _col3, _col4), count(DISTINCT _col1, _col2, _col4), count(DISTINCT _col1, _col2, _col3, _col4) - keys: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) + aggregations: count($f0), count(), count($f1), count($f2), count($f3), count($f4), count(DISTINCT $f1), count(DISTINCT $f2), count(DISTINCT $f3), count(DISTINCT $f4), count(DISTINCT $f1, $f2), count(DISTINCT $f2, $f3), count(DISTINCT $f3, $f4), count(DISTINCT $f1, $f4), count(DISTINCT $f1, $f3), count(DISTINCT $f2, $f4), count(DISTINCT $f1, $f2, $f3), count(DISTINCT $f2, $f3, $f4), count(DISTINCT $f1, $f3, $f4), count(DISTINCT $f1, $f2, $f4), count(DISTINCT $f1, $f2, $f3, $f4) + keys: $f1 (type: int), $f2 (type: int), $f3 (type: int), $f4 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE @@ -129,15 +133,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19, $f20 + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint), $f4 (type: bigint), $f5 (type: bigint), $f6 (type: bigint), $f7 (type: bigint), $f8 (type: bigint), $f9 (type: bigint), $f10 (type: bigint), $f11 (type: bigint), $f12 (type: bigint), $f13 (type: bigint), $f14 (type: bigint), $f15 (type: bigint), $f16 (type: bigint), $f17 (type: bigint), $f18 (type: bigint), $f19 (type: bigint), $f20 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19, $f20 + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -168,31 +176,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: abcd - Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE + expressions: a (type: int), b (type: int), c (type: int) + outputColumnNames: a, b, c + Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + key expressions: a (type: int), b (type: int), c (type: int) sort order: +++ - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int) + Map-reduce partition columns: a (type: int) + Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0), sum(VALUE._col0) + aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0), sum(KEY._col1:0._col0) keys: KEY._col0 (type: int) mode: complete - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: a, $f1, $f2, $f3 + Statistics: Num rows: 3 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: int), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint) + outputColumnNames: a, $f1, $f2, $f3 + Statistics: Num rows: 3 Data size: 39 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 39 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -208,10 +219,10 @@ POSTHOOK: query: select a, count(distinct b), count(distinct c), sum(d) from abc POSTHOOK: type: QUERY POSTHOOK: Input: default@abcd #### A masked pattern was here #### -10 2 2 10 -100 1 1 3 -12 1 2 9 -NULL 1 1 6 +10 2 2 1200 +100 1 1 100 +12 1 2 100 +NULL 1 1 35 PREHOOK: query: explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd PREHOOK: type: QUERY POSTHOOK: query: explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd @@ -229,25 +240,29 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 + outputColumnNames: $f1, $f2, $f3, $f4 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) + key expressions: $f1 (type: int), $f2 (type: int), $f3 (type: int), $f4 (type: int) sort order: ++++ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - aggregations: count(1), count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) + aggregations: count(KEY._col0:0._col0), count(), count(KEY._col0:0._col0), count(KEY._col0:0._col0), count(KEY._col0:0._col0), count(KEY._col0:0._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) mode: complete - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19, $f20 Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint), $f4 (type: bigint), $f5 (type: bigint), $f6 (type: bigint), $f7 (type: bigint), $f8 (type: bigint), $f9 (type: bigint), $f10 (type: bigint), $f11 (type: bigint), $f12 (type: bigint), $f13 (type: bigint), $f14 (type: bigint), $f15 (type: bigint), $f16 (type: bigint), $f17 (type: bigint), $f18 (type: bigint), $f19 (type: bigint), $f20 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19, $f20 Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -263,4 +278,4 @@ POSTHOOK: query: select count(1), count(*), count(a), count(b), count(c), count( POSTHOOK: type: QUERY POSTHOOK: Input: default@abcd #### A masked pattern was here #### -7 7 6 6 6 7 3 3 6 7 4 5 6 6 5 6 4 5 5 5 4 +6 7 6 6 6 6 3 3 6 7 4 5 6 6 5 6 4 5 5 5 4 diff --git a/ql/src/test/results/clientpositive/cp_sel.q.out b/ql/src/test/results/clientpositive/cp_sel.q.out index a2c9fe0..06ec3f3 100644 --- a/ql/src/test/results/clientpositive/cp_sel.q.out +++ b/ql/src/test/results/clientpositive/cp_sel.q.out @@ -17,17 +17,17 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: 1 (type: int) sort order: + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) + value expressions: key (type: string), value (type: string) Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), 'hello' (type: string), 'world' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: VALUE.key (type: string), VALUE.value (type: string), 'hello' (type: string), 'world' (type: string) + outputColumnNames: key, value, ds, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 @@ -92,7 +92,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), 'hello' (type: string), 'world' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/create_genericudaf.q.out b/ql/src/test/results/clientpositive/create_genericudaf.q.out index f74c3f3..40cc3ab 100644 --- a/ql/src/test/results/clientpositive/create_genericudaf.q.out +++ b/ql/src/test/results/clientpositive/create_genericudaf.q.out @@ -40,11 +40,11 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: substr(value, 5) (type: string) - outputColumnNames: _col1 + expressions: 1 (type: int), substr(value, 5) (type: string) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: test_avg(1), test_avg(_col1) + aggregations: test_avg($f0), test_avg($f1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -56,15 +56,19 @@ STAGE PLANS: Group By Operator aggregations: test_avg(VALUE._col0), test_avg(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: double), $f1 (type: double) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/create_view.q.out b/ql/src/test/results/clientpositive/create_view.q.out index 1038d01..60da504 100644 --- a/ql/src/test/results/clientpositive/create_view.q.out +++ b/ql/src/test/results/clientpositive/create_view.q.out @@ -189,14 +189,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: view2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 18.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '18' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/cross_join.q.out b/ql/src/test/results/clientpositive/cross_join.q.out index a6dcd28..1f8c5f9 100644 --- a/ql/src/test/results/clientpositive/cross_join.q.out +++ b/ql/src/test/results/clientpositive/cross_join.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [src, src2]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- current explain select src.key from src join src src2 PREHOOK: type: QUERY @@ -18,14 +18,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + value expressions: key (type: string) TableScan - alias: src + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE @@ -39,15 +39,19 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -55,7 +59,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [src, src2]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- ansi cross join explain select src.key from src cross join src src2 PREHOOK: type: QUERY @@ -75,14 +79,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + value expressions: key (type: string) TableScan - alias: src + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE @@ -96,15 +100,19 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -134,44 +142,48 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/cross_product_check_1.q.out b/ql/src/test/results/clientpositive/cross_product_check_1.q.out index 3ab418a..5dc8745 100644 --- a/ql/src/test/results/clientpositive/cross_product_check_1.q.out +++ b/ql/src/test/results/clientpositive/cross_product_check_1.q.out @@ -28,7 +28,7 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@src POSTHOOK: Output: database:default POSTHOOK: Output: default@B -Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select * from A join B PREHOOK: type: QUERY POSTHOOK: query: explain select * from A join B @@ -46,23 +46,23 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) + value expressions: key (type: string), value (type: string) TableScan alias: b Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) + value expressions: key (type: string), value (type: string) Reduce Operator Tree: Join Operator condition map: @@ -70,15 +70,19 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -234,17 +238,21 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0 Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -261,12 +269,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -348,17 +360,21 @@ STAGE PLANS: 1 outputColumnNames: _col0 Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -375,12 +391,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 5 Data size: 51 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 51 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -467,12 +487,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -496,13 +520,17 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce @@ -538,17 +566,21 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0 Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -565,12 +597,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/cross_product_check_2.q.out b/ql/src/test/results/clientpositive/cross_product_check_2.q.out index 6910b40..cdd47b6 100644 --- a/ql/src/test/results/clientpositive/cross_product_check_2.q.out +++ b/ql/src/test/results/clientpositive/cross_product_check_2.q.out @@ -28,7 +28,7 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@src POSTHOOK: Output: database:default POSTHOOK: Output: default@B -Warning: Map Join MAPJOIN[11][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: explain select * from A join B PREHOOK: type: QUERY POSTHOOK: query: explain select * from A join B @@ -42,17 +42,17 @@ STAGE PLANS: Stage: Stage-4 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:b + b Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:b + b TableScan alias: b Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: @@ -67,7 +67,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -75,15 +75,19 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -234,16 +238,20 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0 Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -252,12 +260,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-8 Map Reduce Local Work @@ -351,16 +363,20 @@ STAGE PLANS: 1 outputColumnNames: _col0 Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -369,12 +385,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 5 Data size: 47 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 47 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-8 Map Reduce Local Work @@ -424,8 +444,8 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[45][bigTable=?] in task 'Stage-7:MAPRED' is a cross product -Warning: Map Join MAPJOIN[38][bigTable=?] in task 'Stage-6:MAPRED' is a cross product +Warning: Map Join MAPJOIN[47][bigTable=?] in task 'Stage-7:MAPRED' is a cross product +Warning: Map Join MAPJOIN[39][bigTable=?] in task 'Stage-6:MAPRED' is a cross product Warning: Shuffle Join JOIN[21][tables = [ss, od1]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: explain select * from (select A.key from A group by key) ss join @@ -474,12 +494,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-8 Conditional Operator @@ -510,13 +534,17 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -546,13 +574,17 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -578,13 +610,17 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-12 Map Reduce Local Work @@ -622,16 +658,20 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0 Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -640,12 +680,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/ctas_colname.q.out b/ql/src/test/results/clientpositive/ctas_colname.q.out index 232d505..4a1ec9e 100644 --- a/ql/src/test/results/clientpositive/ctas_colname.q.out +++ b/ql/src/test/results/clientpositive/ctas_colname.q.out @@ -20,9 +20,14 @@ create table summary as select *, key + 1, concat(value, value) from src limit 2 POSTHOOK: type: CREATETABLE_AS_SELECT STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-0 - Stage-2 depends on stages: Stage-3 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 + Stage-8 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-8 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 @@ -33,31 +38,28 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), (UDFToDouble(key) + 1.0) (type: double), concat(value, value) (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, _o__c1, _o__c2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + File Output Operator + compressed: false Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: double), _col3 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: double), VALUE._col3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.summary + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.summary + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -65,10 +67,10 @@ STAGE PLANS: hdfs directory: true #### A masked pattern was here #### - Stage: Stage-3 + Stage: Stage-8 Create Table Operator: Create Table - columns: key string, value string, c1 double, c2 string + columns: key string, value string, _o__c1 double, _o__c2 string input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat serde name: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -77,6 +79,36 @@ STAGE PLANS: Stage: Stage-2 Stats-Aggr Operator + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.summary + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.summary + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: create table summary as select *, key + 1, concat(value, value) from src limit 20 PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@src @@ -97,8 +129,8 @@ POSTHOOK: Input: default@summary key string value string -c1 double -c2 string +_o__c1 double +_o__c2 string # Detailed Table Information Database: default @@ -181,32 +213,32 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col0: string, _col1: string + output shape: key: string, value: string type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col1 - partition by: _col0 + order by: value + partition by: key raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col1 + alias: $win$_col_2 + arguments: value name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), rank_window_0 (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), value (type: string), $win$_col_2 (type: int) + outputColumnNames: key, value, rank_window_0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -226,7 +258,7 @@ STAGE PLANS: Stage: Stage-3 Create Table Operator: Create Table - columns: key string, value string, rr int + columns: key string, value string, rank_window_0 int input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat serde name: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -255,7 +287,7 @@ POSTHOOK: Input: default@x4 key string value string -rr int +rank_window_0 int # Detailed Table Information Database: default @@ -322,10 +354,9 @@ create table x5 as select *, lead(key,1) over(partition by key order by value) a POSTHOOK: type: CREATETABLE_AS_SELECT STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-0 - Stage-3 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-1 + Stage-3 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 @@ -342,67 +373,44 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col0: string, _col1: string + output shape: key: string, value: string type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col1 - partition by: _col0 + order by: value + partition by: key raw input shape: window functions: window function definition - alias: lead_window_0 - arguments: _col0, 1 + alias: $win$_col_4 + arguments: key, 1 name: lead window function: GenericUDAFLeadEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), lead_window_0 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), value (type: string), $win$_col_4 (type: string) + outputColumnNames: key, value, lead_window_0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.x5 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.x5 Stage: Stage-0 Move Operator @@ -410,16 +418,16 @@ STAGE PLANS: hdfs directory: true #### A masked pattern was here #### - Stage: Stage-4 + Stage: Stage-3 Create Table Operator: Create Table - columns: key string, value string, lead1 string + columns: key string, value string, lead_window_0 string input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat serde name: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.x5 - Stage: Stage-3 + Stage: Stage-2 Stats-Aggr Operator PREHOOK: query: create table x5 as select *, lead(key,1) over(partition by key order by value) as lead1 from src limit 20 @@ -442,7 +450,7 @@ POSTHOOK: Input: default@x5 key string value string -lead1 string +lead_window_0 string # Detailed Table Information Database: default @@ -520,11 +528,11 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: a:src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), (UDFToDouble(key) + 1.0) (type: double) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, _o__c1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -553,7 +561,7 @@ STAGE PLANS: Stage: Stage-8 Create Table Operator: Create Table - columns: key string, value string, _c1 double + columns: key string, value string, _o__c1 double input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat serde name: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -612,7 +620,7 @@ POSTHOOK: Input: default@x6 key string value string -_c1 double +_o__c1 double # Detailed Table Information Database: default @@ -688,15 +696,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(value) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -711,16 +719,20 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, $f2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), $f2 (type: bigint) + outputColumnNames: key, value, $f2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.x7 + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.x7 Stage: Stage-0 Move Operator @@ -731,7 +743,7 @@ STAGE PLANS: Stage: Stage-3 Create Table Operator: Create Table - columns: _col0 string, _col1 string, _c1 bigint + columns: key string, value string, $f2 bigint input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat serde name: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -758,9 +770,9 @@ POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@x7 # col_name data_type comment -_col0 string -_col1 string -_c1 bigint +key string +value string +$f2 bigint # Detailed Table Information Database: default @@ -1120,18 +1132,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 9.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(value) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -1146,16 +1158,20 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, $f2 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), $f2 (type: bigint) + outputColumnNames: key, value, $f2 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.x8 + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.x8 Stage: Stage-0 Move Operator @@ -1166,7 +1182,7 @@ STAGE PLANS: Stage: Stage-3 Create Table Operator: Create Table - columns: _col0 string, _col1 string, _c1 bigint + columns: key string, value string, $f2 bigint input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat serde name: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -1193,9 +1209,9 @@ POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@x8 # col_name data_type comment -_col0 string -_col1 string -_c1 bigint +key string +value string +$f2 bigint # Detailed Table Information Database: default @@ -1251,18 +1267,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 9.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) + aggregations: max(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -1277,14 +1293,14 @@ STAGE PLANS: aggregations: max(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col1 is not null (type: boolean) + predicate: $f1 is not null (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: $f1 (type: string), key (type: string) + outputColumnNames: _o__c0, key Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1304,7 +1320,7 @@ STAGE PLANS: Stage: Stage-3 Create Table Operator: Create Table - columns: _c0 string, key string + columns: _o__c0 string, key string input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat serde name: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -1331,7 +1347,7 @@ POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@x9 # col_name data_type comment -_c0 string +_o__c0 string key string # Detailed Table Information diff --git a/ql/src/test/results/clientpositive/ctas_uses_database_location.q.out b/ql/src/test/results/clientpositive/ctas_uses_database_location.q.out index 554ae48..fc4573b 100644 --- a/ql/src/test/results/clientpositive/ctas_uses_database_location.q.out +++ b/ql/src/test/results/clientpositive/ctas_uses_database_location.q.out @@ -46,7 +46,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/cte_1.q.out b/ql/src/test/results/clientpositive/cte_1.q.out index e80967f..d0f5368 100644 --- a/ql/src/test/results/clientpositive/cte_1.q.out +++ b/ql/src/test/results/clientpositive/cte_1.q.out @@ -17,14 +17,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: q1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = '5') (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '5' (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -74,14 +74,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: a:q1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = '5') (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '5' (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -131,14 +131,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: a:q1:q2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = '5') (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '5' (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/cte_2.q.out b/ql/src/test/results/clientpositive/cte_2.q.out index a8bc760..93afc67 100644 --- a/ql/src/test/results/clientpositive/cte_2.q.out +++ b/ql/src/test/results/clientpositive/cte_2.q.out @@ -40,8 +40,8 @@ select * POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@s1 -POSTHOOK: Lineage: s1.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: s1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: s1.key SIMPLE [(src)q1:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: s1.value SIMPLE [(src)q1:src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from s1 PREHOOK: type: QUERY PREHOOK: Input: default@s1 diff --git a/ql/src/test/results/clientpositive/decimal_precision.q.out b/ql/src/test/results/clientpositive/decimal_precision.q.out index 8d67e2a..d517203 100644 --- a/ql/src/test/results/clientpositive/decimal_precision.q.out +++ b/ql/src/test/results/clientpositive/decimal_precision.q.out @@ -539,10 +539,10 @@ STAGE PLANS: Statistics: Num rows: 23 Data size: 2661 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: dec Statistics: Num rows: 23 Data size: 2661 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), sum(_col0) + aggregations: avg(dec), sum(dec) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE @@ -554,15 +554,19 @@ STAGE PLANS: Group By Operator aggregations: avg(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: decimal(24,14)), $f1 (type: decimal(30,10)) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/decimal_udf.q.out b/ql/src/test/results/clientpositive/decimal_udf.q.out index 338b754..eec8769 100644 --- a/ql/src/test/results/clientpositive/decimal_udf.q.out +++ b/ql/src/test/results/clientpositive/decimal_udf.q.out @@ -43,7 +43,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key + key) (type: decimal(21,10)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -110,7 +110,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key + CAST( value AS decimal(10,0))) (type: decimal(21,10)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -177,7 +177,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) + (UDFToDouble(value) / 2.0)) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -244,7 +244,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) + 1.0) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -313,7 +313,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key - key) (type: decimal(21,10)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -380,7 +380,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key - CAST( value AS decimal(10,0))) (type: decimal(21,10)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -447,7 +447,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) - (UDFToDouble(value) / 2.0)) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -514,7 +514,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) - 1.0) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -583,7 +583,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key * key) (type: decimal(38,20)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -653,7 +653,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE ListSink @@ -705,7 +705,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key * CAST( value AS decimal(10,0))) (type: decimal(31,10)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -772,7 +772,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) * (UDFToDouble(value) / 2.0)) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -839,7 +839,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) * 2.0) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -908,7 +908,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key / 0) (type: decimal(22,12)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 @@ -941,7 +941,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) / null) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 @@ -977,7 +977,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 239 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key / key) (type: decimal(38,24)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 2 Data size: 239 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1043,7 +1043,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 239 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key / CAST( value AS decimal(10,0))) (type: decimal(31,21)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 2 Data size: 239 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1099,7 +1099,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 239 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) / (UDFToDouble(value) / 2.0)) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 2 Data size: 239 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1152,7 +1152,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (1.0 + (UDFToDouble(key) / 2.0)) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1221,7 +1221,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: abs(key) (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1291,11 +1291,11 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1), count(_col1), avg(_col1) - keys: _col0 (type: int) + aggregations: sum($f1), count($f1), avg($f1) + keys: $f0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE @@ -1310,11 +1310,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1), avg(VALUE._col2) keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), (_col1 / CAST( _col2 AS decimal(19,0))) (type: decimal(38,23)), _col3 (type: decimal(24,14)), _col1 (type: decimal(30,10)) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: $f0 (type: int), ($f1 / CAST( $f2 AS decimal(19,0))) (type: decimal(38,23)), $f3 (type: decimal(24,14)), $f1 (type: decimal(30,10)) + outputColumnNames: value, _o__c1, _o__c2, _o__c3 Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1328,14 +1328,14 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: value (type: int) sort order: + Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(38,23)), _col2 (type: decimal(24,14)), _col3 (type: decimal(30,10)) + value expressions: _o__c1 (type: decimal(38,23)), _o__c2 (type: decimal(24,14)), _o__c3 (type: decimal(30,10)) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: decimal(38,23)), VALUE._col1 (type: decimal(24,14)), VALUE._col2 (type: decimal(30,10)) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: KEY.reducesinkkey0 (type: int), VALUE._o__c1 (type: decimal(38,23)), VALUE._o__c2 (type: decimal(24,14)), VALUE._o__c3 (type: decimal(30,10)) + outputColumnNames: value, _o__c1, _o__c2, _o__c3 Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1395,7 +1395,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (- key) (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1464,7 +1464,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1533,7 +1533,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ceil(key) (type: decimal(11,0)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1602,7 +1602,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: floor(key) (type: decimal(11,0)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1671,7 +1671,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: round(key, 2) (type: decimal(13,2)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1740,7 +1740,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: power(key, 2) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1809,7 +1809,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ((key + 1) % (key / 2)) (type: decimal(22,12)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1878,11 +1878,11 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev(_col1), variance(_col1) - keys: _col0 (type: int) + aggregations: stddev($f1), variance($f1) + keys: $f0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE @@ -1897,15 +1897,19 @@ STAGE PLANS: aggregations: stddev(VALUE._col0), variance(VALUE._col1) keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: int), $f1 (type: double), $f2 (type: double) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1957,11 +1961,11 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(_col1), var_samp(_col1) - keys: _col0 (type: int) + aggregations: stddev_samp($f1), var_samp($f1) + keys: $f0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE @@ -1976,15 +1980,19 @@ STAGE PLANS: aggregations: stddev_samp(VALUE._col0), var_samp(VALUE._col1) keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: int), $f1 (type: double), $f2 (type: double) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2035,11 +2043,11 @@ STAGE PLANS: alias: decimal_udf Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + expressions: key (type: decimal(20,10)), 3 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: histogram_numeric(_col0, 3) + aggregations: histogram_numeric($f0, $f1) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -2051,15 +2059,19 @@ STAGE PLANS: Group By Operator aggregations: histogram_numeric(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: array>) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2095,10 +2107,10 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE @@ -2110,15 +2122,19 @@ STAGE PLANS: Group By Operator aggregations: min(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: decimal(20,10)) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2154,10 +2170,10 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE @@ -2169,15 +2185,19 @@ STAGE PLANS: Group By Operator aggregations: max(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: decimal(20,10)) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2213,10 +2233,10 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 3 Data size: 359 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -2228,15 +2248,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/decimal_udf2.q.out b/ql/src/test/results/clientpositive/decimal_udf2.q.out index 1302947..f85774c 100644 --- a/ql/src/test/results/clientpositive/decimal_udf2.q.out +++ b/ql/src/test/results/clientpositive/decimal_udf2.q.out @@ -48,7 +48,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: NaN (type: double), NaN (type: double), 1.4711276743037347 (type: double), -0.8390715290764524 (type: double), -0.5440211108893698 (type: double), 0.6483608274590866 (type: double), 0.17453292519943295 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6 Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -105,7 +105,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 22026.465794806718 (type: double), 2.302585092994046 (type: double), 2.302585092994046 (type: double), 1.0 (type: double), log(10, value) (type: double), log(value, 10) (type: double), 1.0 (type: double), 3.1622776601683795 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7 Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/display_colstats_tbllvl.q.out b/ql/src/test/results/clientpositive/display_colstats_tbllvl.q.out index 7c91248..280df6a 100644 --- a/ql/src/test/results/clientpositive/display_colstats_tbllvl.q.out +++ b/ql/src/test/results/clientpositive/display_colstats_tbllvl.q.out @@ -85,12 +85,15 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + outputColumnNames: _col0, _col1, _col2 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work @@ -194,26 +197,29 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - GlobalTableId: 0 + Select Operator + expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + outputColumnNames: _col0, _col1, _col2 + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 + NumFilesPerFileSink: 1 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types struct:struct:struct - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types struct:struct:struct + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Column Stats Work @@ -318,12 +324,15 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work diff --git a/ql/src/test/results/clientpositive/distinct_stats.q.out b/ql/src/test/results/clientpositive/distinct_stats.q.out index 36049be..431376a 100644 --- a/ql/src/test/results/clientpositive/distinct_stats.q.out +++ b/ql/src/test/results/clientpositive/distinct_stats.q.out @@ -43,11 +43,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: a, b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT b) + keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -61,11 +61,11 @@ STAGE PLANS: aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: a, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 + expressions: $f1 (type: bigint) + outputColumnNames: _o__c0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -100,10 +100,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: b (type: string) - outputColumnNames: _col0 + outputColumnNames: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: b (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -116,15 +116,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: b Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: b (type: string) + outputColumnNames: b Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -151,11 +155,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string) - outputColumnNames: _col0 + outputColumnNames: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: a (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -170,15 +174,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: a, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: a (type: string), $f1 (type: bigint) + outputColumnNames: a, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/dynamic_partition_skip_default.q.out b/ql/src/test/results/clientpositive/dynamic_partition_skip_default.q.out index a209ae9..f170f1e 100644 --- a/ql/src/test/results/clientpositive/dynamic_partition_skip_default.q.out +++ b/ql/src/test/results/clientpositive/dynamic_partition_skip_default.q.out @@ -132,7 +132,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: intcol (type: string) - outputColumnNames: _col0 + outputColumnNames: intcol Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE ListSink @@ -226,7 +226,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: intcol (type: string) - outputColumnNames: _col0 + outputColumnNames: intcol Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE ListSink @@ -374,7 +374,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: intcol (type: string) - outputColumnNames: _col0 + outputColumnNames: intcol Statistics: Num rows: 2 Data size: 2 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out b/ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out index eeb5847..45dd29c 100644 --- a/ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out +++ b/ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out @@ -92,18 +92,22 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - keys: _col2 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: true - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: sum(hash(_col2,_col3)) + keys: _col2 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: true + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -421,12 +425,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1-subquery1:unionsrc-subquery1-subquery1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -438,11 +444,11 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst1' (type: string), _col0 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: 'tst1' (type: string), $f0 (type: bigint) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true @@ -458,7 +464,7 @@ STAGE PLANS: Union Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + expressions: key (type: char(4)), UDFToInteger(value) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -473,7 +479,7 @@ STAGE PLANS: Union Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + expressions: key (type: char(4)), UDFToInteger(value) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -488,7 +494,7 @@ STAGE PLANS: Union Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + expressions: key (type: char(4)), UDFToInteger(value) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -556,12 +562,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1-subquery2:unionsrc-subquery1-subquery2:s2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -573,11 +581,11 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst2' (type: string), _col0 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: 'tst2' (type: string), $f0 (type: bigint) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true @@ -590,12 +598,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery2:unionsrc-subquery2:s3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -607,11 +617,11 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst3' (type: string), _col0 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: 'tst3' (type: string), $f0 (type: bigint) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true @@ -665,12 +675,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1:unionsrc1-subquery1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -682,11 +694,11 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst1' (type: string), UDFToString(_col0) (type: string) - outputColumnNames: _col0, _col1 + expressions: 'tst1' (type: string), UDFToString($f0) (type: string) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true @@ -702,83 +714,89 @@ STAGE PLANS: Union Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: s1 + alias: null-subquery2:unionsrc1-subquery2:s2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 10.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan Union Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: s1 + alias: null-subquery2:unionsrc2-subquery2:s4 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 10.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 27889 Data size: 15171616 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: true + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 27889 Data size: 15171616 Basic stats: COMPLETE Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: true + Statistics: Num rows: 27889 Data size: 15171616 Basic stats: COMPLETE Column stats: PARTIAL + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1:unionsrc2-subquery1:s3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -790,11 +808,11 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst1' (type: string), UDFToString(_col0) (type: string) - outputColumnNames: _col0, _col1 + expressions: 'tst1' (type: string), UDFToString($f0) (type: string) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true @@ -1348,11 +1366,15 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int) + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: int) TableScan alias: inventory Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1362,11 +1384,15 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int) + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: int) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: int), KEY.reducesinkkey0 (type: int) diff --git a/ql/src/test/results/clientpositive/dynpart_sort_optimization2.q.out b/ql/src/test/results/clientpositive/dynpart_sort_optimization2.q.out index cb0eb58..4c67988 100644 --- a/ql/src/test/results/clientpositive/dynpart_sort_optimization2.q.out +++ b/ql/src/test/results/clientpositive/dynpart_sort_optimization2.q.out @@ -91,16 +91,20 @@ STAGE PLANS: Filter Operator predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + outputColumnNames: ss_sold_date_sk, ss_net_paid_inc_tax, ss_net_profit Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) - sort order: +++ - Map-reduce partition columns: _col0 (type: int) + Group By Operator + keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) + sort order: +++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: float), KEY._col2 (type: float) @@ -546,16 +550,20 @@ STAGE PLANS: Filter Operator predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + outputColumnNames: ss_sold_date_sk, ss_net_paid_inc_tax, ss_net_profit Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) - sort order: +++ - Map-reduce partition columns: _col0 (type: int) + Group By Operator + keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) + sort order: +++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: float), KEY._col2 (type: float) @@ -1055,16 +1063,20 @@ STAGE PLANS: Filter Operator predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + outputColumnNames: ss_sold_date_sk, ss_net_paid_inc_tax, ss_net_profit Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) - sort order: +++ - Map-reduce partition columns: _col0 (type: int) + Group By Operator + keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) + sort order: +++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -1537,30 +1549,30 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col1, _col2 + expressions: 'day' (type: string), key (type: string), value (type: string) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col2) - keys: 'day' (type: string), _col1 (type: string) + aggregations: count($f2) + keys: $f0 (type: char(3)), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: _col0 (type: char(3)), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: _col0 (type: char(3)), _col1 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string) + keys: KEY._col0 (type: char(3)), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int), _col0 (type: string) + expressions: UDFToInteger($f1) (type: int), UDFToInteger($f2) (type: int), $f0 (type: char(3)) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -1653,30 +1665,30 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col1, _col2 + expressions: 'day' (type: string), key (type: string), value (type: string) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col2) - keys: 'day' (type: string), _col1 (type: string) + aggregations: count($f2) + keys: $f0 (type: char(3)), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: _col0 (type: char(3)), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: _col0 (type: char(3)) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string) + keys: KEY._col0 (type: char(3)), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int), _col0 (type: string) + expressions: UDFToInteger($f1) (type: int), UDFToInteger($f2) (type: int), $f0 (type: char(3)) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/escape_orderby1.q.out b/ql/src/test/results/clientpositive/escape_orderby1.q.out index b95caf1..4535b40 100644 --- a/ql/src/test/results/clientpositive/escape_orderby1.q.out +++ b/ql/src/test/results/clientpositive/escape_orderby1.q.out @@ -19,16 +19,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -63,16 +63,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/exec_parallel_column_stats.q.out b/ql/src/test/results/clientpositive/exec_parallel_column_stats.q.out index 2e96bb6..c3fd784 100644 --- a/ql/src/test/results/clientpositive/exec_parallel_column_stats.q.out +++ b/ql/src/test/results/clientpositive/exec_parallel_column_stats.q.out @@ -27,12 +27,15 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: struct), _col1 (type: struct) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work diff --git a/ql/src/test/results/clientpositive/explain_dependency.q.out b/ql/src/test/results/clientpositive/explain_dependency.q.out index fa4dc59..617ca50 100644 --- a/ql/src/test/results/clientpositive/explain_dependency.q.out +++ b/ql/src/test/results/clientpositive/explain_dependency.q.out @@ -107,17 +107,17 @@ PREHOOK: query: EXPLAIN DEPENDENCY SELECT * FROM V2 PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN DEPENDENCY SELECT * FROM V2 POSTHOOK: type: QUERY -{"input_partitions":[{"partitionName":"default@srcpart@ds=2008-04-08/hr=11"},{"partitionName":"default@srcpart@ds=2008-04-08/hr=12"},{"partitionName":"default@srcpart@ds=2008-04-09/hr=11"},{"partitionName":"default@srcpart@ds=2008-04-09/hr=12"}],"input_tables":[{"tablename":"default@v2","tabletype":"VIRTUAL_VIEW"},{"tablename":"default@srcpart","tabletype":"MANAGED_TABLE","tableParents":"[default@v2]"}]} +{"input_partitions":[{"partitionParents":"[default@v2]","partitionName":"default@srcpart@ds=2008-04-08/hr=11"},{"partitionParents":"[default@v2]","partitionName":"default@srcpart@ds=2008-04-08/hr=12"},{"partitionParents":"[default@v2]","partitionName":"default@srcpart@ds=2008-04-09/hr=11"},{"partitionParents":"[default@v2]","partitionName":"default@srcpart@ds=2008-04-09/hr=12"}],"input_tables":[{"tablename":"default@v2","tabletype":"VIRTUAL_VIEW"},{"tablename":"default@srcpart","tabletype":"MANAGED_TABLE","tableParents":"[default@v2]"}]} PREHOOK: query: EXPLAIN DEPENDENCY SELECT * FROM V3 PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN DEPENDENCY SELECT * FROM V3 POSTHOOK: type: QUERY -{"input_partitions":[{"partitionName":"default@srcpart@ds=2008-04-08/hr=11"},{"partitionName":"default@srcpart@ds=2008-04-08/hr=12"},{"partitionName":"default@srcpart@ds=2008-04-09/hr=11"},{"partitionName":"default@srcpart@ds=2008-04-09/hr=12"}],"input_tables":[{"tablename":"default@v3","tabletype":"VIRTUAL_VIEW"},{"tablename":"default@v2","tabletype":"VIRTUAL_VIEW","tableParents":"[default@v3]"},{"tablename":"default@src","tabletype":"MANAGED_TABLE","tableParents":"[default@v3]"},{"tablename":"default@srcpart","tabletype":"MANAGED_TABLE","tableParents":"[default@v2]"}]} +{"input_partitions":[{"partitionParents":"[default@v2]","partitionName":"default@srcpart@ds=2008-04-08/hr=11"},{"partitionParents":"[default@v2]","partitionName":"default@srcpart@ds=2008-04-08/hr=12"},{"partitionParents":"[default@v2]","partitionName":"default@srcpart@ds=2008-04-09/hr=11"},{"partitionParents":"[default@v2]","partitionName":"default@srcpart@ds=2008-04-09/hr=12"}],"input_tables":[{"tablename":"default@v3","tabletype":"VIRTUAL_VIEW"},{"tablename":"default@v2","tabletype":"VIRTUAL_VIEW","tableParents":"[default@v3]"},{"tablename":"default@src","tabletype":"MANAGED_TABLE","tableParents":"[default@v3]"},{"tablename":"default@srcpart","tabletype":"MANAGED_TABLE","tableParents":"[default@v2]"}]} PREHOOK: query: EXPLAIN DEPENDENCY SELECT * FROM V4 PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN DEPENDENCY SELECT * FROM V4 POSTHOOK: type: QUERY -{"input_partitions":[{"partitionName":"default@srcpart@ds=2008-04-08/hr=11"},{"partitionName":"default@srcpart@ds=2008-04-08/hr=12"},{"partitionName":"default@srcpart@ds=2008-04-09/hr=11"},{"partitionName":"default@srcpart@ds=2008-04-09/hr=12"}],"input_tables":[{"tablename":"default@v4","tabletype":"VIRTUAL_VIEW"},{"tablename":"default@v1","tabletype":"VIRTUAL_VIEW","tableParents":"[default@v4]"},{"tablename":"default@v2","tabletype":"VIRTUAL_VIEW","tableParents":"[default@v4]"},{"tablename":"default@src","tabletype":"MANAGED_TABLE","tableParents":"[default@v4, default@v1]"},{"tablename":"default@srcpart","tabletype":"MANAGED_TABLE","tableParents":"[default@v2]"}]} +{"input_partitions":[{"partitionParents":"[default@v2]","partitionName":"default@srcpart@ds=2008-04-08/hr=11"},{"partitionParents":"[default@v2]","partitionName":"default@srcpart@ds=2008-04-08/hr=12"},{"partitionParents":"[default@v2]","partitionName":"default@srcpart@ds=2008-04-09/hr=11"},{"partitionParents":"[default@v2]","partitionName":"default@srcpart@ds=2008-04-09/hr=12"}],"input_tables":[{"tablename":"default@v4","tabletype":"VIRTUAL_VIEW"},{"tablename":"default@v1","tabletype":"VIRTUAL_VIEW","tableParents":"[default@v4]"},{"tablename":"default@v2","tabletype":"VIRTUAL_VIEW","tableParents":"[default@v4]"},{"tablename":"default@src","tabletype":"MANAGED_TABLE","tableParents":"[default@v4, default@v1]"},{"tablename":"default@srcpart","tabletype":"MANAGED_TABLE","tableParents":"[default@v2]"}]} PREHOOK: query: -- The table should show up in the explain dependency even if none -- of the partitions are selected. CREATE VIEW V5 as SELECT * FROM srcpart where ds = '10' diff --git a/ql/src/test/results/clientpositive/explain_logical.q.out b/ql/src/test/results/clientpositive/explain_logical.q.out index 545034a..d9246e8 100644 --- a/ql/src/test/results/clientpositive/explain_logical.q.out +++ b/ql/src/test/results/clientpositive/explain_logical.q.out @@ -100,17 +100,17 @@ TOK_QUERY LOGICAL PLAN: -$hdt$_0:srcpart +srcpart TableScan (TS_0) alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_2) - expressions: key (type: string) - outputColumnNames: _col0 + Select Operator (SEL_1) + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator (GBY_4) - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE @@ -124,15 +124,19 @@ $hdt$_0:srcpart aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - File Output Operator (FS_8) - compressed: false + Select Operator (SEL_7) + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator (FS_8) + compressed: false + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe PREHOOK: query: EXPLAIN LOGICAL SELECT key, count(1) FROM (SELECT key, value FROM src) subq1 GROUP BY key @@ -180,39 +184,43 @@ TOK_QUERY LOGICAL PLAN: -$hdt$_0:src +subq1:src TableScan (TS_0) - alias: src + alias: subq1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator (SEL_1) - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator (GBY_3) - aggregations: count(1) - keys: _col0 (type: string) + Group By Operator (GBY_2) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_4) + Reduce Output Operator (RS_3) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) - Group By Operator (GBY_5) + Group By Operator (GBY_4) aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator (FS_7) - compressed: false + Select Operator (SEL_5) + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator (FS_6) + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe PREHOOK: query: EXPLAIN LOGICAL SELECT * FROM ( @@ -278,32 +286,36 @@ TOK_QUERY LOGICAL PLAN: -null-subquery1:$hdt$_0-subquery1:src +null-subquery1:s1-subquery1:src TableScan (TS_0) - alias: src + alias: null-subquery1:s1-subquery1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator (SEL_1) expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Union (UNION_5) + Union (UNION_7) Statistics: Num rows: 2500 Data size: 26560 Basic stats: COMPLETE Column stats: NONE - File Output Operator (FS_7) - compressed: false + Select Operator (SEL_8) + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 2500 Data size: 26560 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -null-subquery2:$hdt$_0-subquery2:srcpart + File Output Operator (FS_9) + compressed: false + Statistics: Num rows: 2500 Data size: 26560 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +null-subquery2:s1-subquery2:srcpart TableScan (TS_2) - alias: srcpart + alias: null-subquery2:s1-subquery2:srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_4) + Select Operator (SEL_3) expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Union (UNION_5) + Union (UNION_7) Statistics: Num rows: 2500 Data size: 26560 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: EXPLAIN LOGICAL @@ -357,34 +369,33 @@ TOK_QUERY LOGICAL PLAN: -$hdt$_0:s2 - TableScan (TS_0) - alias: s2 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_12) +s1 + TableScan (TS_5) + alias: s1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator (FIL_13) predicate: key is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_2) - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_6) - key expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator (SEL_6) + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator (RS_8) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Join Operator (JOIN_9) condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Select Operator (SEL_10) - expressions: _col3 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + expressions: key0 (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE File Output Operator (FS_11) compressed: false @@ -393,29 +404,30 @@ $hdt$_0:s2 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -$hdt$_1:s1 - TableScan (TS_3) - alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_13) +s2 + TableScan (TS_0) + alias: s2 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Filter Operator (FIL_12) predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_4) - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_8) - key expressions: _col0 (type: string) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator (SEL_1) + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator (RS_4) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Join Operator (JOIN_9) condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: -- With views @@ -441,13 +453,13 @@ TOK_QUERY LOGICAL PLAN: -src +v1:src TableScan (TS_0) - alias: src + alias: v1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator (SEL_1) expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink (OP_3) @@ -472,15 +484,15 @@ TOK_QUERY LOGICAL PLAN: -srcpart +v2:srcpart TableScan (TS_0) - alias: srcpart + alias: v2:srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_2) + Select Operator (SEL_1) expressions: ds (type: string), key (type: string), value (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: ds, key, value Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - ListSink (OP_5) + ListSink (OP_6) PREHOOK: query: EXPLAIN LOGICAL SELECT * FROM V3 PREHOOK: type: QUERY @@ -503,65 +515,65 @@ TOK_QUERY LOGICAL PLAN: -$hdt$_0:$hdt$_0:srcpart +v3:src1:srcpart TableScan (TS_0) - alias: srcpart + alias: v3:src1:srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_14) + Filter Operator (FIL_13) predicate: key is not null (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_2) + Select Operator (SEL_1) expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_8) - key expressions: _col0 (type: string) + Reduce Output Operator (RS_5) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Join Operator (JOIN_11) + Join Operator (JOIN_10) condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_12) - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 + Select Operator (SEL_11) + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - File Output Operator (FS_13) + File Output Operator (FS_12) compressed: false Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -$hdt$_1:src2 - TableScan (TS_5) - alias: src2 +v3:src2 + TableScan (TS_6) + alias: v3:src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_15) + Filter Operator (FIL_14) predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_6) + Select Operator (SEL_7) expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_10) - key expressions: _col0 (type: string) + Reduce Output Operator (RS_9) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Join Operator (JOIN_11) + value expressions: value (type: string) + Join Operator (JOIN_10) condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: EXPLAIN LOGICAL SELECT * FROM V4 @@ -585,96 +597,96 @@ TOK_QUERY LOGICAL PLAN: -$hdt$_0:srcpart - TableScan (TS_0) - alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_16) +v4:src1:src + TableScan (TS_6) + alias: v4:src1:src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator (FIL_18) predicate: key is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_2) - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_8) - key expressions: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator (SEL_7) + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator (RS_9) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Join Operator (JOIN_13) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Join Operator (JOIN_14) condition map: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col1, _col2, _col4 + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: value, key0, value1 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_14) - expressions: _col2 (type: string), _col1 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2 + Select Operator (SEL_15) + expressions: key0 (type: string), value (type: string), value1 (type: string) + outputColumnNames: key, value1, value2 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - File Output Operator (FS_15) + File Output Operator (FS_16) compressed: false Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -$hdt$_1:src - TableScan (TS_3) - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE +v4:src2:srcpart + TableScan (TS_0) + alias: v4:src2:srcpart + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator (FIL_17) predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_4) - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_10) - key expressions: _col0 (type: string) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator (SEL_1) + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator (RS_5) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Join Operator (JOIN_13) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Join Operator (JOIN_14) condition map: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col1, _col2, _col4 + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: value, key0, value1 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE -$hdt$_2:src - TableScan (TS_5) - alias: src +v4:src3 + TableScan (TS_10) + alias: v4:src3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_18) + Filter Operator (FIL_19) predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_6) + Select Operator (SEL_11) expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_12) - key expressions: _col0 (type: string) + Reduce Output Operator (RS_13) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Join Operator (JOIN_13) + value expressions: value (type: string) + Join Operator (JOIN_14) condition map: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col1, _col2, _col4 + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: value, key0, value1 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: -- The table should show up in the explain logical even if none @@ -712,18 +724,18 @@ TOK_QUERY LOGICAL PLAN: -srcpart +v5:srcpart TableScan (TS_0) - alias: srcpart + alias: v5:srcpart Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Filter Operator (FIL_4) + Filter Operator (FIL_5) predicate: (ds = '10') (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator (SEL_2) + Select Operator (SEL_1) expressions: key (type: string), value (type: string), '10' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - ListSink (OP_5) + ListSink (OP_6) PREHOOK: query: EXPLAIN LOGICAL SELECT s1.key, s1.cnt, s2.value FROM (SELECT key, count(value) as cnt FROM src GROUP BY key) s1 JOIN src s2 ON (s1.key = s2.key) ORDER BY s1.key PREHOOK: type: QUERY @@ -800,92 +812,92 @@ TOK_QUERY LOGICAL PLAN: -$hdt$_0:src - TableScan (TS_0) - alias: src +s1:src + TableScan (TS_4) + alias: s1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator (FIL_18) predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_1) - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_10) - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Join Operator (JOIN_13) - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_14) - expressions: _col0 (type: string), _col3 (type: bigint), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_15) - key expressions: _col0 (type: string) - sort order: + - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint), _col2 (type: string) - Select Operator (SEL_16) - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator (FS_17) - compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -$hdt$_1:$hdt$_1:src - TableScan (TS_2) - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_19) - predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_3) + Select Operator (SEL_5) expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator (GBY_5) - aggregations: count(_col1) - keys: _col0 (type: string) + Group By Operator (GBY_7) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_6) + Reduce Output Operator (RS_8) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) - Group By Operator (GBY_7) + Group By Operator (GBY_9) aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_12) - key expressions: _col0 (type: string) + Reduce Output Operator (RS_10) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Join Operator (JOIN_13) + value expressions: $f1 (type: bigint) + Join Operator (JOIN_11) condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator (SEL_12) + expressions: key (type: string), $f1 (type: bigint), value (type: string) + outputColumnNames: key, cnt, value + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator (RS_13) + key expressions: key (type: string) + sort order: + + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions: cnt (type: bigint), value (type: string) + Select Operator (SEL_14) + expressions: KEY.reducesinkkey0 (type: string), VALUE.cnt (type: bigint), VALUE.value (type: string) + outputColumnNames: key, cnt, value + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator (FS_15) + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +s2 + TableScan (TS_0) + alias: s2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator (FIL_17) + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator (SEL_1) + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator (RS_3) + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Join Operator (JOIN_11) + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, $f1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/explain_rearrange.q.out b/ql/src/test/results/clientpositive/explain_rearrange.q.out index a4671d3..3c6b5f3 100644 --- a/ql/src/test/results/clientpositive/explain_rearrange.q.out +++ b/ql/src/test/results/clientpositive/explain_rearrange.q.out @@ -87,28 +87,34 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-9 Conditional Operator @@ -254,28 +260,34 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -352,28 +364,34 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Conditional Operator @@ -519,28 +537,34 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-10 Fetch Operator @@ -617,28 +641,34 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -656,28 +686,34 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Conditional Operator @@ -882,28 +918,34 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -921,28 +963,34 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Conditional Operator diff --git a/ql/src/test/results/clientpositive/extrapolate_part_stats_full.q.out b/ql/src/test/results/clientpositive/extrapolate_part_stats_full.q.out index 0f6b15d..78f3ff5 100644 --- a/ql/src/test/results/clientpositive/extrapolate_part_stats_full.q.out +++ b/ql/src/test/results/clientpositive/extrapolate_part_stats_full.q.out @@ -136,7 +136,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 362 + totalSize 369 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -179,7 +179,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 382 + totalSize 389 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -208,7 +208,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: state (type: string) - outputColumnNames: _col0 + outputColumnNames: state Statistics: Num rows: 6 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -269,7 +269,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 362 + totalSize 369 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -312,7 +312,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 382 + totalSize 389 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -341,7 +341,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -469,7 +469,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 277 + totalSize 281 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -513,7 +513,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 279 + totalSize 283 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -557,7 +557,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 261 + totalSize 265 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -601,7 +601,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 261 + totalSize 265 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -630,7 +630,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: state (type: string) - outputColumnNames: _col0 + outputColumnNames: state Statistics: Num rows: 6 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -688,7 +688,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 277 + totalSize 281 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -732,7 +732,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 279 + totalSize 283 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -776,7 +776,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 261 + totalSize 265 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -820,7 +820,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 261 + totalSize 265 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -849,7 +849,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE ListSink diff --git a/ql/src/test/results/clientpositive/extrapolate_part_stats_partial.q.out b/ql/src/test/results/clientpositive/extrapolate_part_stats_partial.q.out index 1fdeb90..b9c5525 100644 --- a/ql/src/test/results/clientpositive/extrapolate_part_stats_partial.q.out +++ b/ql/src/test/results/clientpositive/extrapolate_part_stats_partial.q.out @@ -153,7 +153,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 362 + totalSize 369 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -196,7 +196,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 383 + totalSize 390 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -239,7 +239,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 404 + totalSize 410 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -282,7 +282,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 412 + totalSize 419 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -311,7 +311,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: state (type: string) - outputColumnNames: _col0 + outputColumnNames: state Statistics: Num rows: 20 Data size: 1780 Basic stats: COMPLETE Column stats: PARTIAL ListSink @@ -372,7 +372,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 362 + totalSize 369 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -415,7 +415,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 383 + totalSize 390 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -458,7 +458,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 404 + totalSize 410 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -501,7 +501,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 412 + totalSize 419 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -530,7 +530,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 20 Data size: 1860 Basic stats: COMPLETE Column stats: PARTIAL ListSink @@ -604,7 +604,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 362 + totalSize 369 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -647,7 +647,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 383 + totalSize 390 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -690,7 +690,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 404 + totalSize 410 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -733,7 +733,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 412 + totalSize 419 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -762,7 +762,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: state (type: string) - outputColumnNames: _col0 + outputColumnNames: state Statistics: Num rows: 20 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -819,7 +819,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 362 + totalSize 369 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -862,7 +862,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 383 + totalSize 390 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -905,7 +905,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 404 + totalSize 410 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -948,7 +948,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 412 + totalSize 419 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -977,7 +977,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: PARTIAL ListSink @@ -1106,7 +1106,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 281 + totalSize 286 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1150,7 +1150,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 291 + totalSize 295 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1194,7 +1194,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 298 + totalSize 302 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1238,7 +1238,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 277 + totalSize 281 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1282,7 +1282,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 272 + totalSize 276 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1326,7 +1326,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 283 + totalSize 288 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1370,7 +1370,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 292 + totalSize 297 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1414,7 +1414,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 261 + totalSize 265 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1458,7 +1458,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 261 + totalSize 265 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1502,7 +1502,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 294 + totalSize 298 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1546,7 +1546,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 291 + totalSize 295 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1575,7 +1575,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: state (type: string) - outputColumnNames: _col0 + outputColumnNames: state Statistics: Num rows: 20 Data size: 1760 Basic stats: COMPLETE Column stats: PARTIAL ListSink @@ -1633,7 +1633,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 281 + totalSize 286 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1677,7 +1677,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 291 + totalSize 295 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1721,7 +1721,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 298 + totalSize 302 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1765,7 +1765,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 277 + totalSize 281 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1809,7 +1809,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 272 + totalSize 276 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1853,7 +1853,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 283 + totalSize 288 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1897,7 +1897,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 292 + totalSize 297 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1941,7 +1941,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 261 + totalSize 265 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1985,7 +1985,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 261 + totalSize 265 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -2029,7 +2029,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 294 + totalSize 298 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -2073,7 +2073,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_2d { string state, i32 locid} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 291 + totalSize 295 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -2102,7 +2102,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: state (type: string), locid (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: state, locid Statistics: Num rows: 20 Data size: 1840 Basic stats: COMPLETE Column stats: PARTIAL ListSink diff --git a/ql/src/test/results/clientpositive/extrapolate_part_stats_partial_ndv.q.out b/ql/src/test/results/clientpositive/extrapolate_part_stats_partial_ndv.q.out index 81ac963..fb9f099 100644 --- a/ql/src/test/results/clientpositive/extrapolate_part_stats_partial_ndv.q.out +++ b/ql/src/test/results/clientpositive/extrapolate_part_stats_partial_ndv.q.out @@ -230,7 +230,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 521 + totalSize 531 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -273,7 +273,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 553 + totalSize 562 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -316,7 +316,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 571 + totalSize 580 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -359,7 +359,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 593 + totalSize 602 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -388,7 +388,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: state (type: string), locid (type: double), cnt (type: decimal(10,0)), zip (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, cnt, zip Statistics: Num rows: 20 Data size: 4260 Basic stats: COMPLETE Column stats: PARTIAL ListSink @@ -543,7 +543,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 521 + totalSize 531 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -586,7 +586,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 553 + totalSize 562 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -629,7 +629,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 571 + totalSize 580 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -672,7 +672,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 593 + totalSize 602 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -701,7 +701,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: state (type: string), locid (type: double), cnt (type: decimal(10,0)), zip (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, cnt, zip Statistics: Num rows: 20 Data size: 4220 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -1379,7 +1379,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: state (type: string), locid (type: int), cnt (type: decimal(10,0)), zip (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: state, locid, cnt, zip Statistics: Num rows: 20 Data size: 4160 Basic stats: COMPLETE Column stats: PARTIAL ListSink diff --git a/ql/src/test/results/clientpositive/fetch_aggregation.q.out b/ql/src/test/results/clientpositive/fetch_aggregation.q.out index 121d6a4..0304605 100644 --- a/ql/src/test/results/clientpositive/fetch_aggregation.q.out +++ b/ql/src/test/results/clientpositive/fetch_aggregation.q.out @@ -17,10 +17,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0), sum(_col0), avg(_col0), min(_col0), max(_col0), std(_col0), variance(_col0) + aggregations: count(key), sum(key), avg(key), min(key), max(key), std(key), variance(key) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE @@ -38,9 +38,13 @@ STAGE PLANS: Group By Operator aggregations: count(_col0), sum(_col1), avg(_col2), min(_col3), max(_col4), std(_col5), variance(_col6) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE - ListSink + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6 + Statistics: Num rows: 1 Data size: 392 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: double), $f2 (type: double), $f3 (type: string), $f4 (type: string), $f5 (type: double), $f6 (type: double) + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6 + Statistics: Num rows: 1 Data size: 392 Basic stats: COMPLETE Column stats: NONE + ListSink PREHOOK: query: select count(key),sum(key),avg(key),min(key),max(key),std(key),variance(key) from src PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out b/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out index af42d5c..7d71d61 100644 --- a/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out +++ b/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out @@ -21,50 +21,50 @@ STAGE PLANS: alias: f Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((value = '2008-04-08') or (value = '2008-04-09')) and key is not null) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: ((value = '2008-04-08') or (value = '2008-04-09')) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) TableScan - alias: f + alias: m Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((value is not null and (value <> '')) and key is not null) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + predicate: (value is not null and (value <> '')) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, value0 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((_col1 = '2008-04-08') and (_col3 = '2008-04-08')) or (_col1 = '2008-04-09')) (type: boolean) - Statistics: Num rows: 205 Data size: 2177 Basic stats: COMPLETE Column stats: NONE + predicate: ((value0 <> '') and (((value = '2008-04-08') and (value0 = '2008-04-08')) or (value = '2008-04-09'))) (type: boolean) + Statistics: Num rows: 412 Data size: 4376 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 205 Data size: 2177 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value0 (type: string) + outputColumnNames: key, value0 + Statistics: Num rows: 412 Data size: 4376 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -77,42 +77,42 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: value0 (type: string) sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 205 Data size: 2177 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + Map-reduce partition columns: value0 (type: string) + Statistics: Num rows: 412 Data size: 4376 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: string) TableScan - alias: f + alias: g Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value is not null and (value <> '')) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: value (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col4 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + 0 value0 (type: string) + 1 value (type: string) + outputColumnNames: key, value1 + Statistics: Num rows: 453 Data size: 4813 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 453 Data size: 4813 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 453 Data size: 4813 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -147,50 +147,50 @@ STAGE PLANS: alias: f Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((value) IN ('2008-04-08', '2008-04-10') or (value = '2008-04-09')) and key is not null) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: ((value) IN ('2008-04-08', '2008-04-10') or (value = '2008-04-09')) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) TableScan - alias: f + alias: m Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((value is not null and (value <> '')) and key is not null) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + predicate: (value is not null and (value <> '')) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, value0 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((_col1) IN ('2008-04-08', '2008-04-10') and (_col3 = '2008-04-08')) or (_col1 = '2008-04-09')) (type: boolean) - Statistics: Num rows: 205 Data size: 2177 Basic stats: COMPLETE Column stats: NONE + predicate: ((value0 <> '') and (((value) IN ('2008-04-08', '2008-04-10') and (value0 = '2008-04-08')) or (value = '2008-04-09'))) (type: boolean) + Statistics: Num rows: 412 Data size: 4376 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 205 Data size: 2177 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value0 (type: string) + outputColumnNames: key, value0 + Statistics: Num rows: 412 Data size: 4376 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -203,42 +203,42 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: value0 (type: string) sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 205 Data size: 2177 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + Map-reduce partition columns: value0 (type: string) + Statistics: Num rows: 412 Data size: 4376 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: string) TableScan - alias: f + alias: g Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value is not null and (value <> '')) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: value (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col4 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + 0 value0 (type: string) + 1 value (type: string) + outputColumnNames: key, value1 + Statistics: Num rows: 453 Data size: 4813 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 453 Data size: 4813 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 453 Data size: 4813 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -280,51 +280,51 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t2 + alias: t4:t2 Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 1.0) (type: boolean) Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: c_int (type: int), c_float (type: float) - outputColumnNames: _col1, _col2 + expressions: c_float (type: float), c_int (type: int) + outputColumnNames: c_float, c_int Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: '1.0' (type: string) sort order: + Map-reduce partition columns: '1.0' (type: string) Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: float) + value expressions: c_int (type: int), c_float (type: float) TableScan - alias: t3 + alias: t4:t3:t3 Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((c_int = 1) and (UDFToDouble(key) = 1.0)) (type: boolean) Statistics: Num rows: 5 Data size: 65 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c_float (type: float) - outputColumnNames: _col2 + outputColumnNames: c_float Statistics: Num rows: 5 Data size: 65 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: '1.0' (type: string) sort order: + Map-reduce partition columns: '1.0' (type: string) Statistics: Num rows: 5 Data size: 65 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: float) + value expressions: 1 (type: int), c_float (type: float) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col5 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, c_int, c_float, c_int0, c_float0 Statistics: Num rows: 11 Data size: 144 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((_col2 + _col5) > 2.0) or ((_col1 + 1) > 2)) (type: boolean) - Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE + predicate: ((((c_float + c_float0) > 2.0) or ((c_int + c_int0) > 2)) and (UDFToDouble(key) = 1.0)) (type: boolean) + Statistics: Num rows: 3 Data size: 39 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 39 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -353,18 +353,19 @@ STAGE PLANS: key expressions: '1.0' (type: string) sort order: + Map-reduce partition columns: '1.0' (type: string) - Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 39 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 11 Data size: 144 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '1.0' (type: string) - outputColumnNames: _col0 + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 11 Data size: 144 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/filter_numeric.q.out b/ql/src/test/results/clientpositive/filter_numeric.q.out index d1965df..f631a86 100644 --- a/ql/src/test/results/clientpositive/filter_numeric.q.out +++ b/ql/src/test/results/clientpositive/filter_numeric.q.out @@ -48,7 +48,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: string), value (type: string), hr (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, hr Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE ListSink @@ -78,7 +78,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), hr (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, hr Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink @@ -610,7 +610,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), hr (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1644,7 +1644,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), hr (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, hr Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink @@ -2176,7 +2176,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), hr (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/flatten_and_or.q.out b/ql/src/test/results/clientpositive/flatten_and_or.q.out index 9c51ff3..6400a9b 100644 --- a/ql/src/test/results/clientpositive/flatten_and_or.q.out +++ b/ql/src/test/results/clientpositive/flatten_and_or.q.out @@ -48,7 +48,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/fold_case.q.out b/ql/src/test/results/clientpositive/fold_case.q.out index a9214f3..45505a4 100644 --- a/ql/src/test/results/clientpositive/fold_case.q.out +++ b/ql/src/test/results/clientpositive/fold_case.q.out @@ -19,9 +19,11 @@ STAGE PLANS: predicate: (key = '238') (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -33,15 +35,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -70,9 +76,11 @@ STAGE PLANS: predicate: (key <> '238') (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -84,15 +92,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -120,28 +132,36 @@ STAGE PLANS: Filter Operator predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: + Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator + aggregations: count($f0) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -167,9 +187,11 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -181,15 +203,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -218,9 +244,11 @@ STAGE PLANS: predicate: (key = '238') (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -232,15 +260,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -268,28 +300,36 @@ STAGE PLANS: Filter Operator predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: + Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator + aggregations: count($f0) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -318,9 +358,11 @@ STAGE PLANS: predicate: (key = '238') (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -332,15 +374,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -370,7 +416,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CASE (key) WHEN ('238') THEN (null) ELSE (false) END (type: boolean) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -408,7 +454,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator expressions: null (type: void) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE File Output Operator compressed: false @@ -445,9 +491,11 @@ STAGE PLANS: predicate: (key <> '238') (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -459,15 +507,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/fold_eq_with_case_when.q.out b/ql/src/test/results/clientpositive/fold_eq_with_case_when.q.out index 231d98f..234397d 100644 --- a/ql/src/test/results/clientpositive/fold_eq_with_case_when.q.out +++ b/ql/src/test/results/clientpositive/fold_eq_with_case_when.q.out @@ -45,12 +45,12 @@ STAGE PLANS: predicate: (('1996-03-30' = to_date(l_shipdate)) and ('RAIL' = l_shipmode)) (type: boolean) Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: l_orderkey (type: int), (UDFToDouble(l_partkey) / 1000000.0) (type: double) - outputColumnNames: _col0, _col1 + expressions: l_orderkey (type: int), (UDFToDouble(l_partkey) / 1000000.0) (type: double), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1), sum(1) - keys: _col0 (type: int) + aggregations: sum($f1), sum($f2) + keys: $f0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE @@ -65,11 +65,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), sum(VALUE._col1) keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: double), _col2 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: $f1 (type: double), $f2 (type: bigint) + outputColumnNames: _o__c0, sum_number_of_records_ok Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -105,7 +105,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '238' (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -141,7 +141,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -177,7 +177,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '238' (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -213,7 +213,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/fold_when.q.out b/ql/src/test/results/clientpositive/fold_when.q.out index bf61a7d..b223b06 100644 --- a/ql/src/test/results/clientpositive/fold_when.q.out +++ b/ql/src/test/results/clientpositive/fold_when.q.out @@ -20,7 +20,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -58,7 +58,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -93,7 +93,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink @@ -119,7 +119,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -157,7 +157,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '238' (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -195,7 +195,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '238' (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -230,7 +230,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink @@ -256,7 +256,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -294,7 +294,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '238' (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -332,7 +332,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -367,7 +367,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink @@ -390,7 +390,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink @@ -413,7 +413,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink @@ -439,7 +439,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -474,7 +474,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/folder_predicate.q.out b/ql/src/test/results/clientpositive/folder_predicate.q.out index 1bc1afb..eea4351 100644 --- a/ql/src/test/results/clientpositive/folder_predicate.q.out +++ b/ql/src/test/results/clientpositive/folder_predicate.q.out @@ -41,7 +41,7 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -92,7 +92,7 @@ STAGE PLANS: Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -141,7 +141,7 @@ STAGE PLANS: Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -190,7 +190,7 @@ STAGE PLANS: Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -240,7 +240,7 @@ STAGE PLANS: Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -290,7 +290,7 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -338,7 +338,7 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/fouter_join_ppr.q.out b/ql/src/test/results/clientpositive/fouter_join_ppr.q.out index 087edf2..ec9cfde 100644 --- a/ql/src/test/results/clientpositive/fouter_join_ppr.q.out +++ b/ql/src/test/results/clientpositive/fouter_join_ppr.q.out @@ -118,15 +118,15 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false TableScan alias: b @@ -134,15 +134,15 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string), _col2 (type: string) + value expressions: value (type: string), ds (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -376,11 +376,11 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b] - /srcpart/ds=2008-04-09/hr=11 [$hdt$_1:b] - /srcpart/ds=2008-04-09/hr=12 [$hdt$_1:b] + /src [a] + /srcpart/ds=2008-04-08/hr=11 [b] + /srcpart/ds=2008-04-08/hr=12 [b] + /srcpart/ds=2008-04-09/hr=11 [b] + /srcpart/ds=2008-04-09/hr=12 [b] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -390,37 +390,41 @@ STAGE PLANS: 1 [0, 1] filter predicates: 0 - 1 {(VALUE._col1 = '2008-04-08')} + 1 {(VALUE.ds = '2008-04-08')} keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) and (UDFToDouble(_col2) > 15.0)) and (UDFToDouble(_col2) < 25.0)) (type: boolean) + predicate: ((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key0) > 15.0)) and (UDFToDouble(key0) < 25.0)) (type: boolean) Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns key,value,key0,value0 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -586,15 +590,15 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col1 (type: string), _col2 (type: string) + value expressions: value (type: string), ds (type: string) auto parallelism: false TableScan alias: b @@ -602,15 +606,15 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -844,11 +848,11 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:a] - /srcpart/ds=2008-04-09/hr=11 [$hdt$_0:a] - /srcpart/ds=2008-04-09/hr=12 [$hdt$_0:a] + /src [b] + /srcpart/ds=2008-04-08/hr=11 [a] + /srcpart/ds=2008-04-08/hr=12 [a] + /srcpart/ds=2008-04-09/hr=11 [a] + /srcpart/ds=2008-04-09/hr=12 [a] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -857,20 +861,20 @@ STAGE PLANS: filter mappings: 0 [1, 1] filter predicates: - 0 {(VALUE._col1 = '2008-04-08')} + 0 {(VALUE.ds = '2008-04-08')} 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3, _col4 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) and (UDFToDouble(_col3) > 15.0)) and (UDFToDouble(_col3) < 25.0)) (type: boolean) + predicate: ((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key0) > 15.0)) and (UDFToDouble(key0) < 25.0)) (type: boolean) Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -883,7 +887,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2,_col3 + columns key,value,key0,value0 columns.types string:string:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -1062,15 +1066,15 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false TableScan alias: b @@ -1082,15 +1086,15 @@ STAGE PLANS: Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -1232,44 +1236,48 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b] + /src [a] + /srcpart/ds=2008-04-08/hr=11 [b] + /srcpart/ds=2008-04-08/hr=12 [b] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean) + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns key,value,key0,value0 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -1435,15 +1443,15 @@ STAGE PLANS: Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false TableScan alias: b @@ -1455,15 +1463,15 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -1605,26 +1613,26 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:a] + /src [b] + /srcpart/ds=2008-04-08/hr=11 [a] + /srcpart/ds=2008-04-08/hr=12 [a] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3, _col4 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((UDFToDouble(_col3) > 15.0) and (UDFToDouble(_col3) < 25.0)) (type: boolean) + predicate: ((UDFToDouble(key0) > 15.0) and (UDFToDouble(key0) < 25.0)) (type: boolean) Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1637,7 +1645,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2,_col3 + columns key,value,key0,value0 columns.types string:string:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true diff --git a/ql/src/test/results/clientpositive/gby_star.q.out b/ql/src/test/results/clientpositive/gby_star.q.out index a49f1bf..2c19a76 100644 --- a/ql/src/test/results/clientpositive/gby_star.q.out +++ b/ql/src/test/results/clientpositive/gby_star.q.out @@ -17,11 +17,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) - keys: _col0 (type: string), _col1 (type: string) + aggregations: sum(key) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -36,18 +36,22 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, $f2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), $f2 (type: double) + outputColumnNames: key, value, $f2 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -95,11 +99,11 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) - keys: _col0 (type: string), _col1 (type: string) + aggregations: sum(key) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -114,18 +118,22 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, $f2 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), $f2 (type: double) + outputColumnNames: key, value, $f2 + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -166,18 +174,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) - keys: _col0 (type: string) + aggregations: sum(key) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -192,18 +200,22 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: double) + outputColumnNames: key, $f1 + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -247,19 +259,19 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE TableScan alias: src @@ -269,25 +281,25 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, key0 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string) + aggregations: sum(key0) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE @@ -313,18 +325,22 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: double) + outputColumnNames: key, $f1 + Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/global_limit.q.out b/ql/src/test/results/clientpositive/global_limit.q.out index 7da20d5..925c2f2 100644 --- a/ql/src/test/results/clientpositive/global_limit.q.out +++ b/ql/src/test/results/clientpositive/global_limit.q.out @@ -1101,7 +1101,7 @@ POSTHOOK: query: insert overwrite table gl_tgt select key+1 from (select * from POSTHOOK: type: QUERY POSTHOOK: Input: default@gl_src1 POSTHOOK: Output: default@gl_tgt -POSTHOOK: Lineage: gl_tgt.key EXPRESSION [(gl_src1)gl_src1.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: gl_tgt.key EXPRESSION [(gl_src1)t2:t1:gl_src1.FieldSchema(name:key, type:int, comment:null), ] PREHOOK: query: select * from gl_tgt ORDER BY key ASC PREHOOK: type: QUERY PREHOOK: Input: default@gl_tgt diff --git a/ql/src/test/results/clientpositive/groupby1.q.out b/ql/src/test/results/clientpositive/groupby1.q.out index 785c078..fd38bb2 100644 --- a/ql/src/test/results/clientpositive/groupby1.q.out +++ b/ql/src/test/results/clientpositive/groupby1.q.out @@ -31,14 +31,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), substr(value, 5) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: $f1 (type: string) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) @@ -68,10 +68,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: double) + expressions: UDFToInteger($f0) (type: int), $f1 (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/groupby12.q.out b/ql/src/test/results/clientpositive/groupby12.q.out index 6eb3e96..789d548 100644 --- a/ql/src/test/results/clientpositive/groupby12.q.out +++ b/ql/src/test/results/clientpositive/groupby12.q.out @@ -28,22 +28,22 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - aggregations: count(KEY._col0), count(DISTINCT KEY._col1:0._col0) + aggregations: count(KEY._col1:0._col0), count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: complete - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, $f1, $f2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col1) (type: int), _col2 (type: bigint) + expressions: UDFToInteger($f1) (type: int), $f2 (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -78,7 +78,7 @@ INSERT OVERWRITE TABLE dest1 SELECT COUNT(src.key), COUNT(DISTINCT value) GROUP POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/groupby1_limit.q.out b/ql/src/test/results/clientpositive/groupby1_limit.q.out index 0607258..7a6ff41 100644 --- a/ql/src/test/results/clientpositive/groupby1_limit.q.out +++ b/ql/src/test/results/clientpositive/groupby1_limit.q.out @@ -18,9 +18,8 @@ FROM src INSERT OVERWRITE TABLE dest1 SELECT src.key, sum(substr(src.value,5)) G POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 @@ -31,11 +30,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), substr(value, 5) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string) + aggregations: sum($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -50,46 +49,27 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: + Select Operator + expressions: $f0 (type: string), $f1 (type: double) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 5 Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: double) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: UDFToInteger($f0) (type: int), $f1 (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 Stage: Stage-0 Move Operator @@ -101,7 +81,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1 - Stage: Stage-3 + Stage: Stage-2 Stats-Aggr Operator PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT src.key, sum(substr(src.value,5)) GROUP BY src.key ORDER BY src.key LIMIT 5 diff --git a/ql/src/test/results/clientpositive/groupby1_map.q.out b/ql/src/test/results/clientpositive/groupby1_map.q.out index 7cdf240..0b316a6 100644 --- a/ql/src/test/results/clientpositive/groupby1_map.q.out +++ b/ql/src/test/results/clientpositive/groupby1_map.q.out @@ -30,11 +30,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), substr(value, 5) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string) + aggregations: sum($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -49,10 +49,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: double) + expressions: UDFToInteger($f0) (type: int), $f1 (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out b/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out index 7cdf240..0b316a6 100644 --- a/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out +++ b/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out @@ -30,11 +30,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), substr(value, 5) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string) + aggregations: sum($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -49,10 +49,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: double) + expressions: UDFToInteger($f0) (type: int), $f1 (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/groupby1_map_skew.q.out b/ql/src/test/results/clientpositive/groupby1_map_skew.q.out index be7eeca..b00204e 100644 --- a/ql/src/test/results/clientpositive/groupby1_map_skew.q.out +++ b/ql/src/test/results/clientpositive/groupby1_map_skew.q.out @@ -31,11 +31,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), substr(value, 5) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string) + aggregations: sum($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -74,10 +74,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: double) + expressions: UDFToInteger($f0) (type: int), $f1 (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/groupby1_noskew.q.out b/ql/src/test/results/clientpositive/groupby1_noskew.q.out index ef1fd79..092ec69 100644 --- a/ql/src/test/results/clientpositive/groupby1_noskew.q.out +++ b/ql/src/test/results/clientpositive/groupby1_noskew.q.out @@ -30,23 +30,23 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), substr(value, 5) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: $f1 (type: string) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: complete - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: double) + expressions: UDFToInteger($f0) (type: int), $f1 (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/groupby2_limit.q.out b/ql/src/test/results/clientpositive/groupby2_limit.q.out index ef9531a..473403a 100644 --- a/ql/src/test/results/clientpositive/groupby2_limit.q.out +++ b/ql/src/test/results/clientpositive/groupby2_limit.q.out @@ -18,11 +18,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), substr(value, 5) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string) + aggregations: sum($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -37,28 +37,32 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: string), $f1 (type: double) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double) + value expressions: $f1 (type: double) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: double) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.$f1 (type: double) + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 diff --git a/ql/src/test/results/clientpositive/groupby2_map.q.out b/ql/src/test/results/clientpositive/groupby2_map.q.out index c157ba7..b362547 100644 --- a/ql/src/test/results/clientpositive/groupby2_map.q.out +++ b/ql/src/test/results/clientpositive/groupby2_map.q.out @@ -32,11 +32,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), sum(_col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT $f1), sum($f1) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -51,10 +51,10 @@ STAGE PLANS: aggregations: count(DISTINCT KEY._col1:0._col0), sum(VALUE._col1) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string) + expressions: $f0 (type: string), UDFToInteger($f1) (type: int), concat($f0, $f2) (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -89,7 +89,7 @@ INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1), count(DISTINCT substr(s POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.null, ] POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 diff --git a/ql/src/test/results/clientpositive/groupby2_map_skew.q.out b/ql/src/test/results/clientpositive/groupby2_map_skew.q.out index 813ae5c..8db4bbc 100644 --- a/ql/src/test/results/clientpositive/groupby2_map_skew.q.out +++ b/ql/src/test/results/clientpositive/groupby2_map_skew.q.out @@ -29,11 +29,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), sum(_col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT $f1), sum($f1) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -72,10 +72,10 @@ STAGE PLANS: aggregations: count(VALUE._col0), sum(VALUE._col1) keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string) + expressions: $f0 (type: string), UDFToInteger($f1) (type: int), concat($f0, $f2) (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -110,7 +110,7 @@ INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1), count(DISTINCT substr(s POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.null, ] POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 order by key diff --git a/ql/src/test/results/clientpositive/groupby2_noskew.q.out b/ql/src/test/results/clientpositive/groupby2_noskew.q.out index d3aff42..91c39eb 100644 --- a/ql/src/test/results/clientpositive/groupby2_noskew.q.out +++ b/ql/src/test/results/clientpositive/groupby2_noskew.q.out @@ -32,22 +32,22 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: $f0 (type: string), $f1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: complete - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string) + expressions: $f0 (type: string), UDFToInteger($f1) (type: int), concat($f0, $f2) (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out index 2527fcd..6fa442c 100644 --- a/ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out @@ -31,24 +31,23 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string), value (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: $f0 (type: string), $f1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: string) Reduce Operator Tree: Group By Operator - aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0), sum(DISTINCT KEY._col1:1._col0), count(VALUE._col0) + aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0), sum(DISTINCT KEY._col1:1._col0), count(KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: complete - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: $f0, $f1, $f2, $f3, $f4 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) + expressions: $f0 (type: string), UDFToInteger($f1) (type: int), concat($f0, $f2) (type: string), UDFToInteger($f3) (type: int), UDFToInteger($f4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/groupby3.q.out b/ql/src/test/results/clientpositive/groupby3.q.out index 4247d28..d79e643 100644 --- a/ql/src/test/results/clientpositive/groupby3.q.out +++ b/ql/src/test/results/clientpositive/groupby3.q.out @@ -47,12 +47,12 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(value, 5) (type: string) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator @@ -79,15 +79,15 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2), max(VALUE._col3), min(VALUE._col4), std(VALUE._col5), stddev_samp(VALUE._col6), variance(VALUE._col7), var_samp(VALUE._col8) mode: final - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8 + Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), UDFToDouble(_col3) (type: double), UDFToDouble(_col4) (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double) + expressions: $f0 (type: double), $f1 (type: double), $f2 (type: double), UDFToDouble($f3) (type: double), UDFToDouble($f4) (type: double), $f5 (type: double), $f6 (type: double), $f7 (type: double), $f8 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby3_map.q.out b/ql/src/test/results/clientpositive/groupby3_map.q.out index 405daa9..44758f2 100644 --- a/ql/src/test/results/clientpositive/groupby3_map.q.out +++ b/ql/src/test/results/clientpositive/groupby3_map.q.out @@ -46,11 +46,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(value, 5) (type: string) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), avg(_col0), avg(DISTINCT _col0), max(_col0), min(_col0), std(_col0), stddev_samp(_col0), variance(_col0), var_samp(_col0) - keys: _col0 (type: string) + aggregations: sum($f0), avg($f0), avg(DISTINCT $f0), max($f0), min($f0), std($f0), stddev_samp($f0), variance($f0), var_samp($f0) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -63,15 +63,15 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), avg(VALUE._col1), avg(DISTINCT KEY._col0:0._col0), max(VALUE._col3), min(VALUE._col4), std(VALUE._col5), stddev_samp(VALUE._col6), variance(VALUE._col7), var_samp(VALUE._col8) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8 + Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), UDFToDouble(_col3) (type: double), UDFToDouble(_col4) (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double) + expressions: $f0 (type: double), $f1 (type: double), $f2 (type: double), UDFToDouble($f3) (type: double), UDFToDouble($f4) (type: double), $f5 (type: double), $f6 (type: double), $f7 (type: double), $f8 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -121,7 +121,7 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.null, ] POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c5 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c6 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] diff --git a/ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out index a1d24e8..6857ea3 100644 --- a/ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out @@ -50,11 +50,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(value, 5) (type: string) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), avg(_col0), avg(DISTINCT _col0), max(_col0), min(_col0), std(_col0), stddev_samp(_col0), variance(_col0), var_samp(_col0), sum(DISTINCT _col0), count(DISTINCT _col0) - keys: _col0 (type: string) + aggregations: sum($f0), avg($f0), avg(DISTINCT $f0), max($f0), min($f0), std($f0), stddev_samp($f0), variance($f0), var_samp($f0), sum(DISTINCT $f0), count(DISTINCT $f0) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -67,15 +67,15 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), avg(VALUE._col1), avg(DISTINCT KEY._col0:0._col0), max(VALUE._col3), min(VALUE._col4), std(VALUE._col5), stddev_samp(VALUE._col6), variance(VALUE._col7), var_samp(VALUE._col8), sum(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1 Data size: 248 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10 + Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), UDFToDouble(_col3) (type: double), UDFToDouble(_col4) (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), UDFToDouble(_col10) (type: double) + expressions: $f0 (type: double), $f1 (type: double), $f2 (type: double), UDFToDouble($f3) (type: double), UDFToDouble($f4) (type: double), $f5 (type: double), $f6 (type: double), $f7 (type: double), $f8 (type: double), $f9 (type: double), UDFToDouble($f10) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1 Data size: 248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -131,7 +131,7 @@ POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:st POSTHOOK: Lineage: dest1.c10 EXPRESSION [(src)src.null, ] POSTHOOK: Lineage: dest1.c11 EXPRESSION [(src)src.null, ] POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.null, ] POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c5 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c6 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] diff --git a/ql/src/test/results/clientpositive/groupby3_map_skew.q.out b/ql/src/test/results/clientpositive/groupby3_map_skew.q.out index 5679770..62f75b0 100644 --- a/ql/src/test/results/clientpositive/groupby3_map_skew.q.out +++ b/ql/src/test/results/clientpositive/groupby3_map_skew.q.out @@ -47,11 +47,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(value, 5) (type: string) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), avg(_col0), avg(DISTINCT _col0), max(_col0), min(_col0), std(_col0), stddev_samp(_col0), variance(_col0), var_samp(_col0) - keys: _col0 (type: string) + aggregations: sum($f0), avg($f0), avg(DISTINCT $f0), max($f0), min($f0), std($f0), stddev_samp($f0), variance($f0), var_samp($f0) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -86,15 +86,15 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2), max(VALUE._col3), min(VALUE._col4), std(VALUE._col5), stddev_samp(VALUE._col6), variance(VALUE._col7), var_samp(VALUE._col8) mode: final - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8 + Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), UDFToDouble(_col3) (type: double), UDFToDouble(_col4) (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double) + expressions: $f0 (type: double), $f1 (type: double), $f2 (type: double), UDFToDouble($f3) (type: double), UDFToDouble($f4) (type: double), $f5 (type: double), $f6 (type: double), $f7 (type: double), $f8 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -144,7 +144,7 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.null, ] POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c5 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c6 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] diff --git a/ql/src/test/results/clientpositive/groupby3_noskew.q.out b/ql/src/test/results/clientpositive/groupby3_noskew.q.out index e6c13cf..50f558c 100644 --- a/ql/src/test/results/clientpositive/groupby3_noskew.q.out +++ b/ql/src/test/results/clientpositive/groupby3_noskew.q.out @@ -46,20 +46,20 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(value, 5) (type: string) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator aggregations: sum(KEY._col0:0._col0), avg(KEY._col0:0._col0), avg(DISTINCT KEY._col0:0._col0), max(KEY._col0:0._col0), min(KEY._col0:0._col0), std(KEY._col0:0._col0), stddev_samp(KEY._col0:0._col0), variance(KEY._col0:0._col0), var_samp(KEY._col0:0._col0) mode: complete - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8 Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), UDFToDouble(_col3) (type: double), UDFToDouble(_col4) (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double) + expressions: $f0 (type: double), $f1 (type: double), $f2 (type: double), UDFToDouble($f3) (type: double), UDFToDouble($f4) (type: double), $f5 (type: double), $f6 (type: double), $f7 (type: double), $f8 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out index f6be869..95233b0 100644 --- a/ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out @@ -50,20 +50,20 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(value, 5) (type: string) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator aggregations: sum(KEY._col0:0._col0), avg(KEY._col0:0._col0), avg(DISTINCT KEY._col0:0._col0), max(KEY._col0:0._col0), min(KEY._col0:0._col0), std(KEY._col0:0._col0), stddev_samp(KEY._col0:0._col0), variance(KEY._col0:0._col0), var_samp(KEY._col0:0._col0), sum(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0) mode: complete - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10 Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), UDFToDouble(_col3) (type: double), UDFToDouble(_col4) (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), UDFToDouble(_col10) (type: double) + expressions: $f0 (type: double), $f1 (type: double), $f2 (type: double), UDFToDouble($f3) (type: double), UDFToDouble($f4) (type: double), $f5 (type: double), $f6 (type: double), $f7 (type: double), $f8 (type: double), $f9 (type: double), UDFToDouble($f10) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/groupby4.q.out b/ql/src/test/results/clientpositive/groupby4.q.out index 55313fa..12de5d2 100644 --- a/ql/src/test/results/clientpositive/groupby4.q.out +++ b/ql/src/test/results/clientpositive/groupby4.q.out @@ -33,10 +33,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(key, 1, 1) (type: string) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -66,16 +66,20 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string) + outputColumnNames: $f0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 Stage: Stage-0 Move Operator diff --git a/ql/src/test/results/clientpositive/groupby4_map.q.out b/ql/src/test/results/clientpositive/groupby4_map.q.out index a8a7fbe..ca0e9e7 100644 --- a/ql/src/test/results/clientpositive/groupby4_map.q.out +++ b/ql/src/test/results/clientpositive/groupby4_map.q.out @@ -25,9 +25,11 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -39,10 +41,10 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: UDFToInteger(_col0) (type: int) + expressions: UDFToInteger($f0) (type: int) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator diff --git a/ql/src/test/results/clientpositive/groupby4_map_skew.q.out b/ql/src/test/results/clientpositive/groupby4_map_skew.q.out index 3f38895..6b70ef5 100644 --- a/ql/src/test/results/clientpositive/groupby4_map_skew.q.out +++ b/ql/src/test/results/clientpositive/groupby4_map_skew.q.out @@ -25,9 +25,11 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -39,10 +41,10 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: final - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: UDFToInteger(_col0) (type: int) + expressions: UDFToInteger($f0) (type: int) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator diff --git a/ql/src/test/results/clientpositive/groupby4_noskew.q.out b/ql/src/test/results/clientpositive/groupby4_noskew.q.out index d1936da..24a45bf 100644 --- a/ql/src/test/results/clientpositive/groupby4_noskew.q.out +++ b/ql/src/test/results/clientpositive/groupby4_noskew.q.out @@ -32,27 +32,31 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(key, 1, 1) (type: string) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: complete - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string) + outputColumnNames: $f0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 Stage: Stage-0 Move Operator diff --git a/ql/src/test/results/clientpositive/groupby5.q.out b/ql/src/test/results/clientpositive/groupby5.q.out index 946d685..491e9f4 100644 --- a/ql/src/test/results/clientpositive/groupby5.q.out +++ b/ql/src/test/results/clientpositive/groupby5.q.out @@ -37,14 +37,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), substr(value, 5) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: $f1 (type: string) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) @@ -74,10 +74,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: double) + expressions: UDFToInteger($f0) (type: int), $f1 (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/groupby5_map.q.out b/ql/src/test/results/clientpositive/groupby5_map.q.out index ea8ce4a..d64b1ef 100644 --- a/ql/src/test/results/clientpositive/groupby5_map.q.out +++ b/ql/src/test/results/clientpositive/groupby5_map.q.out @@ -26,10 +26,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -41,15 +41,15 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int) + expressions: UDFToInteger($f0) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby5_map_skew.q.out b/ql/src/test/results/clientpositive/groupby5_map_skew.q.out index c0fced7..97cacbc 100644 --- a/ql/src/test/results/clientpositive/groupby5_map_skew.q.out +++ b/ql/src/test/results/clientpositive/groupby5_map_skew.q.out @@ -26,10 +26,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -41,15 +41,15 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: final - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int) + expressions: UDFToInteger($f0) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby5_noskew.q.out b/ql/src/test/results/clientpositive/groupby5_noskew.q.out index 8de96dc..22eda85 100644 --- a/ql/src/test/results/clientpositive/groupby5_noskew.q.out +++ b/ql/src/test/results/clientpositive/groupby5_noskew.q.out @@ -36,23 +36,23 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), substr(value, 5) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: $f1 (type: string) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: complete - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: double) + expressions: UDFToInteger($f0) (type: int), $f1 (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/groupby6.q.out b/ql/src/test/results/clientpositive/groupby6.q.out index d8cb2ac..5c3549c 100644 --- a/ql/src/test/results/clientpositive/groupby6.q.out +++ b/ql/src/test/results/clientpositive/groupby6.q.out @@ -33,10 +33,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(value, 5, 1) (type: string) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -66,16 +66,20 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string) + outputColumnNames: $f0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 Stage: Stage-0 Move Operator diff --git a/ql/src/test/results/clientpositive/groupby6_map.q.out b/ql/src/test/results/clientpositive/groupby6_map.q.out index b307eba..a75cea2 100644 --- a/ql/src/test/results/clientpositive/groupby6_map.q.out +++ b/ql/src/test/results/clientpositive/groupby6_map.q.out @@ -32,10 +32,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(value, 5, 1) (type: string) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -48,16 +48,20 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string) + outputColumnNames: $f0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 Stage: Stage-0 Move Operator diff --git a/ql/src/test/results/clientpositive/groupby6_map_skew.q.out b/ql/src/test/results/clientpositive/groupby6_map_skew.q.out index c5af47d..3696bb8 100644 --- a/ql/src/test/results/clientpositive/groupby6_map_skew.q.out +++ b/ql/src/test/results/clientpositive/groupby6_map_skew.q.out @@ -33,10 +33,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(value, 5, 1) (type: string) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -71,16 +71,20 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string) + outputColumnNames: $f0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 Stage: Stage-0 Move Operator diff --git a/ql/src/test/results/clientpositive/groupby6_noskew.q.out b/ql/src/test/results/clientpositive/groupby6_noskew.q.out index 43c7400..18776e0 100644 --- a/ql/src/test/results/clientpositive/groupby6_noskew.q.out +++ b/ql/src/test/results/clientpositive/groupby6_noskew.q.out @@ -32,27 +32,31 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(value, 5, 1) (type: string) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: complete - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string) + outputColumnNames: $f0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 Stage: Stage-0 Move Operator diff --git a/ql/src/test/results/clientpositive/groupby7_noskew_multi_single_reducer.q.out b/ql/src/test/results/clientpositive/groupby7_noskew_multi_single_reducer.q.out index cb6c73c..d247772 100644 --- a/ql/src/test/results/clientpositive/groupby7_noskew_multi_single_reducer.q.out +++ b/ql/src/test/results/clientpositive/groupby7_noskew_multi_single_reducer.q.out @@ -63,24 +63,32 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: true - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: true + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: true - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: true + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce diff --git a/ql/src/test/results/clientpositive/groupby_complex_types.q.out b/ql/src/test/results/clientpositive/groupby_complex_types.q.out index 4b561a7..8bf5672 100644 --- a/ql/src/test/results/clientpositive/groupby_complex_types.q.out +++ b/ql/src/test/results/clientpositive/groupby_complex_types.q.out @@ -111,14 +111,18 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: array), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 Stage: Stage-0 Move Operator @@ -150,14 +154,18 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: map), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2 + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest2 Stage: Stage-1 Move Operator @@ -189,14 +197,18 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: struct), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest3 + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest3 Stage: Stage-2 Move Operator diff --git a/ql/src/test/results/clientpositive/groupby_complex_types_multi_single_reducer.q.out b/ql/src/test/results/clientpositive/groupby_complex_types_multi_single_reducer.q.out index 0564056..c41b061 100644 --- a/ql/src/test/results/clientpositive/groupby_complex_types_multi_single_reducer.q.out +++ b/ql/src/test/results/clientpositive/groupby_complex_types_multi_single_reducer.q.out @@ -84,12 +84,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: array), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -147,12 +151,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: map), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-6 Map Reduce diff --git a/ql/src/test/results/clientpositive/groupby_cube1.q.out b/ql/src/test/results/clientpositive/groupby_cube1.q.out index 62e9c54..9194b81 100644 --- a/ql/src/test/results/clientpositive/groupby_cube1.q.out +++ b/ql/src/test/results/clientpositive/groupby_cube1.q.out @@ -36,32 +36,31 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), val (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 4 Data size: 120 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f1 (type: string), $f2 (type: bigint) + outputColumnNames: key, val, _o__c2 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -121,19 +120,19 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), val (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 4 Data size: 120 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: @@ -141,11 +140,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: $f0, $f1, GROUPING__ID, $f2 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: $f0 (type: string), $f1 (type: string), GROUPING__ID (type: int), $f2 (type: bigint) + outputColumnNames: key, val, grouping__id, _o__c3 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -206,30 +205,29 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), '0' (type: string), _col1 (type: string) + aggregations: count(DISTINCT val) + keys: key (type: string), '0' (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col2:0._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string) + keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col2 + outputColumnNames: key, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true Select Operator - expressions: _col0 (type: string), _col2 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, _o__c1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -278,12 +276,12 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), val (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 120 Basic stats: COMPLETE Column stats: NONE @@ -320,14 +318,13 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: final - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f1 (type: string), $f2 (type: bigint) + outputColumnNames: key, val, _o__c2 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -389,11 +386,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), '0' (type: string), _col1 (type: string) + aggregations: count(DISTINCT val) + keys: key (type: string), '0' (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE @@ -429,14 +426,13 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string) + keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0, _col2 + outputColumnNames: key, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true Select Operator - expressions: _col0 (type: string), _col2 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, _o__c1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out b/ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out index bd92927..54faf4f 100644 --- a/ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out +++ b/ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out @@ -40,24 +40,24 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: q1:t1 Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: int1 (type: int) - outputColumnNames: _col0 + outputColumnNames: int1 Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: int1 (type: int) sort order: + Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int) - outputColumnNames: _col0 + outputColumnNames: int1 Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(DISTINCT _col0) - keys: _col0 (type: int) + aggregations: sum(DISTINCT int1) + keys: int1 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE @@ -82,15 +82,19 @@ STAGE PLANS: aggregations: sum(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: int1, $f1 Statistics: Num rows: 4 Data size: 60 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: int1 (type: int), $f1 (type: bigint) + outputColumnNames: int1, $f1 Statistics: Num rows: 4 Data size: 60 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -115,11 +119,11 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: int1 (type: int) - outputColumnNames: _col0 + outputColumnNames: int1 Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(DISTINCT _col0) - keys: _col0 (type: int) + aggregations: sum(DISTINCT int1) + keys: int1 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE @@ -133,15 +137,19 @@ STAGE PLANS: aggregations: sum(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: int1, $f1 Statistics: Num rows: 4 Data size: 60 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: int1 (type: int), $f1 (type: bigint) + outputColumnNames: int1, $f1 Statistics: Num rows: 4 Data size: 60 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/groupby_grouping_id2.q.out b/ql/src/test/results/clientpositive/groupby_grouping_id2.q.out index 544a7ae..a9340f3 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_id2.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_id2.q.out @@ -55,9 +55,7 @@ GROUP BY GROUPING__ID POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 #### A masked pattern was here #### -0 1 -1 4 -3 6 +1 148 PREHOOK: query: SELECT t1.GROUPING__ID, t2.GROUPING__ID FROM (SELECT GROUPING__ID FROM T1 GROUP BY key,value WITH ROLLUP) t1 JOIN (SELECT GROUPING__ID FROM T1 GROUP BY key, value WITH ROLLUP) t2 @@ -162,9 +160,7 @@ GROUP BY GROUPING__ID POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 #### A masked pattern was here #### -0 1 -1 4 -3 6 +1 148 PREHOOK: query: SELECT t1.GROUPING__ID, t2.GROUPING__ID FROM (SELECT GROUPING__ID FROM T1 GROUP BY key,value WITH ROLLUP) t1 JOIN (SELECT GROUPING__ID FROM T1 GROUP BY key, value WITH ROLLUP) t2 diff --git a/ql/src/test/results/clientpositive/groupby_grouping_sets2.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets2.q.out index 6d44f32..1505a4a 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets2.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets2.q.out @@ -36,11 +36,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string), _col1 (type: string) + keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE @@ -77,14 +77,13 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: final - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: a, b, $f2 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: a (type: string), b (type: string), $f2 (type: bigint) + outputColumnNames: a, b, _o__c2 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -143,11 +142,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string), c (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: a, b, c Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col2) - keys: _col0 (type: string), _col1 (type: string) + aggregations: sum(c) + keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE @@ -184,14 +183,13 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: final - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: a, b, $f2 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: double) - outputColumnNames: _col0, _col1, _col2 + expressions: a (type: string), b (type: string), $f2 (type: double) + outputColumnNames: a, b, _o__c2 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -272,11 +270,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string), (c + d) (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col2) - keys: _col0 (type: string), _col1 (type: string) + aggregations: sum($f2) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE @@ -313,14 +311,13 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: final - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f1 (type: string), $f2 (type: bigint) + outputColumnNames: a, b, _o__c2 Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/groupby_grouping_sets3.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets3.q.out index 5d1a7a8..d54c8ab 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets3.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets3.q.out @@ -55,31 +55,30 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string), c (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: a, b, c Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col2), count() - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + aggregations: avg(c), count() + keys: a (type: string), b (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4 Data size: 288 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 4 Data size: 288 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: struct), _col4 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: avg(VALUE._col0), count(VALUE._col1) - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col3, _col4 + outputColumnNames: a, b, $f2, $f3 Statistics: Num rows: 2 Data size: 144 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: double), _col4 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: a (type: string), b (type: string), $f2 (type: double), $f3 (type: bigint) + outputColumnNames: a, b, _o__c2, _o__c3 Statistics: Num rows: 2 Data size: 144 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -143,11 +142,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string), c (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: a, b, c Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col2), count() - keys: _col0 (type: string), _col1 (type: string) + aggregations: avg(c), count() + keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE @@ -184,14 +183,13 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: avg(VALUE._col0), count(VALUE._col1) - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: final - outputColumnNames: _col0, _col1, _col3, _col4 + outputColumnNames: a, b, $f2, $f3 Statistics: Num rows: 2 Data size: 144 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: double), _col4 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: a (type: string), b (type: string), $f2 (type: double), $f3 (type: bigint) + outputColumnNames: a, b, _o__c2, _o__c3 Statistics: Num rows: 2 Data size: 144 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/groupby_grouping_sets4.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets4.q.out index 6ad483b..21b3b7c 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets4.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets4.q.out @@ -54,18 +54,22 @@ STAGE PLANS: Filter Operator predicate: (a < 3) (type: boolean) Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: a (type: string), b (type: string), '0' (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 144 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Select Operator + expressions: a (type: string), b (type: string) + outputColumnNames: a, b + Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: a (type: string), b (type: string), '0' (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 144 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Statistics: Num rows: 4 Data size: 144 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -111,13 +115,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2 Data size: 79 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint), _col3 (type: string), _col4 (type: string), _col5 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2 Data size: 79 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 79 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce @@ -128,18 +136,22 @@ STAGE PLANS: Filter Operator predicate: (a < 3) (type: boolean) Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: a (type: string), b (type: string), '0' (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 144 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Select Operator + expressions: a (type: string), b (type: string) + outputColumnNames: a, b + Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: a (type: string), b (type: string), '0' (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 144 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Statistics: Num rows: 4 Data size: 144 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -230,18 +242,22 @@ STAGE PLANS: Filter Operator predicate: (a < 3) (type: boolean) Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: a (type: string), b (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: a (type: string), b (type: string) + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Group By Operator + aggregations: count() + keys: a (type: string), b (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -311,13 +327,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2 Data size: 79 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint), _col3 (type: string), _col4 (type: string), _col5 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2 Data size: 79 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 79 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce @@ -328,18 +348,22 @@ STAGE PLANS: Filter Operator predicate: (a < 3) (type: boolean) Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: a (type: string), b (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: a (type: string), b (type: string) + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Group By Operator + aggregations: count() + keys: a (type: string), b (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) diff --git a/ql/src/test/results/clientpositive/groupby_grouping_sets5.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets5.q.out index bd7c2ff..81246e0 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets5.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets5.q.out @@ -38,14 +38,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: subq1:t1 Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE @@ -58,11 +58,11 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + keys: a (type: string), b (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 144 Basic stats: COMPLETE Column stats: NONE @@ -80,20 +80,19 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 4 Data size: 144 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: a, b, $f2 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: a (type: string), b (type: string), $f2 (type: bigint) + outputColumnNames: a, b, _o__c2 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -155,14 +154,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: subq1:t1 Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE @@ -175,11 +174,11 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string), _col1 (type: string) + keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE @@ -227,14 +226,13 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: final - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: a, b, $f2 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: a (type: string), b (type: string), $f2 (type: bigint) + outputColumnNames: a, b, _o__c2 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/groupby_grouping_sets6.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets6.q.out index d807d44..97c7e15 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets6.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets6.q.out @@ -35,39 +35,42 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: res:t1 Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(a) = 5.0) (type: boolean) + Select Operator + expressions: a (type: string), b (type: string) + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '5' (type: string), b (type: string) - outputColumnNames: _col0, _col1 + Filter Operator + predicate: (UDFToDouble(a) = 5.0) (type: boolean) Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + keys: a (type: string), b (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true - File Output Operator - compressed: false + Select Operator + expressions: a (type: string), b (type: string) + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -110,39 +113,42 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: res:t1 Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(a) = 5.0) (type: boolean) + Select Operator + expressions: a (type: string), b (type: string) + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '5' (type: string), b (type: string) - outputColumnNames: _col0, _col1 + Filter Operator + predicate: (UDFToDouble(a) = 5.0) (type: boolean) Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + keys: a (type: string), b (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true - File Output Operator - compressed: false + Select Operator + expressions: a (type: string), b (type: string) + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/groupby_map_ppr.q.out b/ql/src/test/results/clientpositive/groupby_map_ppr.q.out index 51780f5..4b74149 100644 --- a/ql/src/test/results/clientpositive/groupby_map_ppr.q.out +++ b/ql/src/test/results/clientpositive/groupby_map_ppr.q.out @@ -110,11 +110,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), sum(_col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT $f1), sum($f1) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -222,18 +222,18 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:src] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:src] + /srcpart/ds=2008-04-08/hr=11 [src] + /srcpart/ds=2008-04-08/hr=12 [src] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), sum(VALUE._col1) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string) + expressions: $f0 (type: string), UDFToInteger($f1) (type: int), concat($f0, $f2) (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -309,7 +309,7 @@ POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.c1 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c1 EXPRESSION [(srcpart)src.null, ] POSTHOOK: Lineage: dest1.c2 EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), (srcpart)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.key EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 diff --git a/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out index ae79b9b..6da4c39 100644 --- a/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out @@ -127,11 +127,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string), value (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), sum(_col1), sum(DISTINCT _col1), count(DISTINCT _col2) - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) + aggregations: count(DISTINCT $f1), sum($f1), sum(DISTINCT $f1), count(DISTINCT $f2) + keys: $f0 (type: string), $f1 (type: string), $f2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -239,18 +239,18 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:src] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:src] + /srcpart/ds=2008-04-08/hr=11 [src] + /srcpart/ds=2008-04-08/hr=12 [src] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), sum(VALUE._col1), sum(DISTINCT KEY._col1:1._col0), count(DISTINCT KEY._col1:2._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: $f0, $f1, $f2, $f3, $f4 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) + expressions: $f0 (type: string), UDFToInteger($f1) (type: int), concat($f0, $f2) (type: string), UDFToInteger($f3) (type: int), UDFToInteger($f4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -326,10 +326,10 @@ POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.c1 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c1 EXPRESSION [(srcpart)src.null, ] POSTHOOK: Lineage: dest1.c2 EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), (srcpart)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c3 EXPRESSION [(srcpart)src.null, ] -POSTHOOK: Lineage: dest1.c4 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c4 EXPRESSION [(srcpart)src.null, ] POSTHOOK: Lineage: dest1.key EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/groupby_multi_single_reducer2.q.out b/ql/src/test/results/clientpositive/groupby_multi_single_reducer2.q.out index 972ed51..03e6980 100644 --- a/ql/src/test/results/clientpositive/groupby_multi_single_reducer2.q.out +++ b/ql/src/test/results/clientpositive/groupby_multi_single_reducer2.q.out @@ -45,12 +45,16 @@ STAGE PLANS: Filter Operator predicate: ((substr(key, 1, 1) < 5) or (substr(key, 1, 1) >= 5)) (type: boolean) Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: substr(key, 1, 1) (type: string), key (type: string) - sort order: ++ - Map-reduce partition columns: substr(key, 1, 1) (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + Reduce Output Operator + key expressions: substr(key, 1, 1) (type: string), key (type: string) + sort order: ++ + Map-reduce partition columns: substr(key, 1, 1) (type: string) + Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Forward Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/groupby_multi_single_reducer3.q.out b/ql/src/test/results/clientpositive/groupby_multi_single_reducer3.q.out index ca66c67..c16f4ba 100644 --- a/ql/src/test/results/clientpositive/groupby_multi_single_reducer3.q.out +++ b/ql/src/test/results/clientpositive/groupby_multi_single_reducer3.q.out @@ -61,12 +61,16 @@ STAGE PLANS: Filter Operator predicate: (((value) IN ('val_400', 'val_500') and (key) IN (400, 450)) or ((value) IN ('val_100', 'val_200', 'val_300') and (key) IN (100, 150, 200))) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Forward Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -227,12 +231,16 @@ STAGE PLANS: Filter Operator predicate: ((((key + key) = 400) or (((key - 100) = 500) and value is not null)) or (((key + key) = 200) or ((key - 100) = 100) or ((key = 300) and value is not null))) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: value (type: string) - sort order: + - Map-reduce partition columns: value (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string) + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: string) Reduce Operator Tree: Forward Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -393,12 +401,16 @@ STAGE PLANS: Filter Operator predicate: (((value) IN ('val_400', 'val_500') and (key) IN (400, 450)) or ((value) IN ('val_100', 'val_200', 'val_300') and (key) IN (100, 150, 200))) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: value (type: string) + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Forward Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -559,12 +571,16 @@ STAGE PLANS: Filter Operator predicate: ((((key + key) = 400) or (((key - 100) = 500) and value is not null)) or (((key + key) = 200) or ((key - 100) = 100) or ((key = 300) and value is not null))) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: value (type: string) - sort order: + - Map-reduce partition columns: value (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string) + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: string) Reduce Operator Tree: Forward Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/groupby_position.q.out b/ql/src/test/results/clientpositive/groupby_position.q.out index 7152101..ca077d1 100644 --- a/ql/src/test/results/clientpositive/groupby_position.q.out +++ b/ql/src/test/results/clientpositive/groupby_position.q.out @@ -46,32 +46,40 @@ STAGE PLANS: Filter Operator predicate: (key < 20) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(DISTINCT substr(value, 5)) - keys: key (type: string), substr(value, 5) (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: count(DISTINCT substr(value, 5)) + keys: key (type: string), substr(value, 5) (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key < 20) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(DISTINCT substr(value, 5)) - keys: key (type: string), value (type: string), substr(value, 5) (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count(DISTINCT substr(value, 5)) + keys: key (type: string), value (type: string), substr(value, 5) (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0) @@ -236,17 +244,21 @@ STAGE PLANS: Filter Operator predicate: (key < 20) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(DISTINCT substr(value, 5)) - keys: key (type: string), substr(value, 5) (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: count(DISTINCT substr(value, 5)) + keys: key (type: string), substr(value, 5) (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key < 20) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -426,18 +438,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: t:b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) <= 20.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -452,27 +464,31 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col1 (type: bigint), _col0 (type: string) + key expressions: $f1 (type: bigint), $f0 (type: string) sort order: -+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -558,17 +574,17 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: c:a:src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 15.0)) and (UDFToDouble(key) < 25.0)) and key is not null) (type: boolean) + predicate: (((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and key is not null) and (UDFToDouble(key) > 15.0)) and (UDFToDouble(key) < 25.0)) (type: boolean) Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE @@ -581,7 +597,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -595,46 +611,50 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + key expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) sort order: --++ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -648,17 +668,17 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: c:b:src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) + predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and key is not null) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE @@ -671,7 +691,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/groupby_ppd.q.out b/ql/src/test/results/clientpositive/groupby_ppd.q.out index 6164a26..3130bab 100644 --- a/ql/src/test/results/clientpositive/groupby_ppd.q.out +++ b/ql/src/test/results/clientpositive/groupby_ppd.q.out @@ -21,66 +21,58 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: c + alias: a-subquery1:b-subquery1:c Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (bar = 1) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: foo (type: int) - outputColumnNames: _col1 + expressions: 1 (type: int), foo (type: int) + outputColumnNames: bar, foo Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: 1 (type: int), _col1 (type: int) + Group By Operator + keys: bar (type: int), foo (type: int) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - keys: _col0 (type: int), _col1 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE TableScan - alias: c + alias: a-subquery2:b-subquery2:d Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (bar = 1) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: foo (type: int) - outputColumnNames: _col1 + expressions: 1 (type: int), foo (type: int) + outputColumnNames: bar, foo Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: 1 (type: int), _col1 (type: int) + Group By Operator + keys: bar (type: int), foo (type: int) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - keys: _col0 (type: int), _col1 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: bar, foo Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col1 (type: int), _col0 (type: int) - outputColumnNames: _col0, _col1 + expressions: foo (type: int), bar (type: int) + outputColumnNames: (tok_table_or_col foo), (tok_table_or_col bar) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/groupby_ppr.q.out b/ql/src/test/results/clientpositive/groupby_ppr.q.out index 393633c..f5891d3 100644 --- a/ql/src/test/results/clientpositive/groupby_ppr.q.out +++ b/ql/src/test/results/clientpositive/groupby_ppr.q.out @@ -110,12 +110,12 @@ STAGE PLANS: GatherStats: false Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: $f0 (type: string), $f1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE tag: -1 auto parallelism: false @@ -215,18 +215,18 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:src] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:src] + /srcpart/ds=2008-04-08/hr=11 [src] + /srcpart/ds=2008-04-08/hr=12 [src] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: complete - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string) + expressions: $f0 (type: string), UDFToInteger($f1) (type: int), concat($f0, $f2) (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out index 6eb3f66..1e680b7 100644 --- a/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out @@ -127,12 +127,12 @@ STAGE PLANS: GatherStats: false Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string), value (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + key expressions: $f0 (type: string), $f1 (type: string), $f2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE tag: -1 auto parallelism: false @@ -232,18 +232,18 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:src] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:src] + /srcpart/ds=2008-04-08/hr=11 [src] + /srcpart/ds=2008-04-08/hr=12 [src] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0), sum(DISTINCT KEY._col1:1._col0), count(DISTINCT KEY._col1:2._col0) keys: KEY._col0 (type: string) mode: complete - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: $f0, $f1, $f2, $f3, $f4 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) + expressions: $f0 (type: string), UDFToInteger($f1) (type: int), concat($f0, $f2) (type: string), UDFToInteger($f3) (type: int), UDFToInteger($f4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -322,7 +322,7 @@ POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), (srcpart)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c3 EXPRESSION [(srcpart)src.null, ] -POSTHOOK: Lineage: dest1.c4 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c4 EXPRESSION [(srcpart)src.null, ] POSTHOOK: Lineage: dest1.key EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/groupby_resolution.q.out b/ql/src/test/results/clientpositive/groupby_resolution.q.out index 7df53f2..d7322f0 100644 --- a/ql/src/test/results/clientpositive/groupby_resolution.q.out +++ b/ql/src/test/results/clientpositive/groupby_resolution.q.out @@ -15,27 +15,31 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -60,27 +64,31 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -106,10 +114,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -142,15 +150,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -176,10 +188,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -212,15 +224,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -245,11 +261,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -264,15 +280,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -297,11 +317,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -316,15 +336,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -350,11 +374,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -393,15 +417,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -427,11 +455,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -470,15 +498,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -609,11 +641,11 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -652,7 +684,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -666,40 +698,40 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: 0 (type: int), _col1 (type: bigint) + key expressions: 0 (type: int), $f1 (type: bigint) sort order: ++ Map-reduce partition columns: 0 (type: int) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: bigint) + value expressions: key (type: string), $f1 (type: bigint) Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: VALUE.key (type: string), VALUE.$f1 (type: bigint) + outputColumnNames: key, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col0: string, _col1: bigint + output shape: key: string, $f1: bigint type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col1 + order by: $f1 partition by: 0 raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col1 + alias: $win$_col_8 + arguments: $f1 name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), rank_window_0 (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), $f1 (type: bigint), $win$_col_8 (type: int) + outputColumnNames: _o__col0, (tok_functionstar count), rank_window_0 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/groupby_rollup1.q.out b/ql/src/test/results/clientpositive/groupby_rollup1.q.out index 8e04d86..de6faab 100644 --- a/ql/src/test/results/clientpositive/groupby_rollup1.q.out +++ b/ql/src/test/results/clientpositive/groupby_rollup1.q.out @@ -36,32 +36,31 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), val (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f1 (type: string), $f2 (type: bigint) + outputColumnNames: key, val, _o__c2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -116,30 +115,29 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), '0' (type: string), _col1 (type: string) + aggregations: count(DISTINCT val) + keys: key (type: string), '0' (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col2:0._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string) + keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col2 + outputColumnNames: key, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true Select Operator - expressions: _col0 (type: string), _col2 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, _o__c1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -188,12 +186,12 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), val (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE @@ -230,14 +228,13 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: final - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f1 (type: string), $f2 (type: bigint) + outputColumnNames: key, val, _o__c2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -293,11 +290,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), '0' (type: string), _col1 (type: string) + aggregations: count(DISTINCT val) + keys: key (type: string), '0' (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE @@ -333,14 +330,13 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string) + keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0, _col2 + outputColumnNames: key, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true Select Operator - expressions: _col0 (type: string), _col2 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, _o__c1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/groupby_sort_10.q.out b/ql/src/test/results/clientpositive/groupby_sort_10.q.out index 2fead26..8cd0a78 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_10.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_10.q.out @@ -41,20 +41,24 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 4 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: final outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string) + outputColumnNames: key Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -109,11 +113,11 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 60 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 8 Data size: 60 Basic stats: COMPLETE Column stats: NONE Group By Operator bucketGroup: true - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 8 Data size: 60 Basic stats: COMPLETE Column stats: NONE @@ -126,15 +130,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 4 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 4 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/groupby_sort_11.q.out b/ql/src/test/results/clientpositive/groupby_sort_11.q.out index adf585d..0015432 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_11.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_11.q.out @@ -41,12 +41,12 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0) + aggregations: count(DISTINCT key) bucketGroup: true - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -59,15 +59,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -104,13 +108,13 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0), count(1), count(_col0), sum(DISTINCT _col0) + aggregations: count(DISTINCT $f0), count($f1), count($f0), sum(DISTINCT $f0) bucketGroup: true - keys: _col0 (type: string) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -123,15 +127,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), sum(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: double) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -168,13 +176,13 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0), count(1), count(_col0), sum(DISTINCT _col0) + aggregations: count(DISTINCT $f0), count($f1), count($f0), sum(DISTINCT $f0) bucketGroup: true - keys: _col0 (type: string) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -189,11 +197,11 @@ STAGE PLANS: aggregations: count(DISTINCT KEY._col1:0._col0), count(VALUE._col1), count(VALUE._col2), sum(DISTINCT KEY._col1:1._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: $f0, $f1, $f2, $f3, $f4 Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint), $f4 (type: double) + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3 Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -243,13 +251,13 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0), count(1), count(_col0), sum(DISTINCT _col0) + aggregations: count(DISTINCT $f0), count($f1), count($f0), sum(DISTINCT $f0) bucketGroup: true - keys: _col0 (type: string) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -264,15 +272,19 @@ STAGE PLANS: aggregations: count(DISTINCT KEY._col1:0._col0), count(VALUE._col1), count(VALUE._col2), sum(DISTINCT KEY._col1:1._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: $f0, $f1, $f2, $f3, $f4 Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint), $f4 (type: double) + outputColumnNames: $f0, $f1, $f2, $f3, $f4 Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -315,11 +327,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) + UDFToDouble(key)) (type: double) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0) - keys: _col0 (type: double) + aggregations: count(DISTINCT $f0) + keys: $f0 (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -331,15 +343,19 @@ STAGE PLANS: Group By Operator aggregations: count(DISTINCT KEY._col0:0._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -374,10 +390,12 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT 1) - keys: 1 (type: int) + aggregations: count(DISTINCT $f0) + keys: $f0 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -389,15 +407,19 @@ STAGE PLANS: Group By Operator aggregations: count(DISTINCT KEY._col0:0._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -435,25 +457,29 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col0:0._col0) mode: complete - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/groupby_sort_1_23.q.out b/ql/src/test/results/clientpositive/groupby_sort_1_23.q.out index 8ba10c5..946ea21 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_1_23.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_1_23.q.out @@ -98,12 +98,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -189,7 +189,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-7 Conditional Operator @@ -457,12 +457,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), val (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -526,17 +526,17 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) + expressions: UDFToInteger($f0) (type: int), $f1 (type: string), UDFToInteger($f2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -684,16 +684,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: subq1:t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -784,7 +784,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [subq1:t1] Stage: Stage-7 Conditional Operator @@ -1010,8 +1010,8 @@ SELECT key, count(1) FROM (SELECT key, val FROM T1) subq1 GROUP BY key POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ] -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)subq1:t1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)subq1:t1.FieldSchema(name:key, type:string, comment:null), ] PREHOOK: query: SELECT * FROM outputTbl1 PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl1 @@ -1092,16 +1092,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: subq1:t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1192,7 +1192,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [subq1:t1] Stage: Stage-7 Conditional Operator @@ -1418,8 +1418,8 @@ SELECT k, count(1) FROM (SELECT key as k, val as v FROM T1) subq1 GROUP BY k POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ] -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)subq1:t1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)subq1:t1.FieldSchema(name:key, type:string, comment:null), ] PREHOOK: query: SELECT * FROM outputTbl1 PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl1 @@ -1500,12 +1500,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col1 + expressions: 1 (type: int), key (type: string) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: 1 (type: int), _col1 (type: string) + aggregations: count($f0) + keys: $f0 (type: int), $f1 (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1591,7 +1591,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-7 Conditional Operator @@ -1863,12 +1863,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + expressions: key (type: string), 1 (type: int), val (type: string) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), 1 (type: int), _col2 (type: string) + aggregations: count($f1) + keys: $f0 (type: string), $f1 (type: int), $f2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -1932,17 +1932,17 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: int), _col2 (type: string), UDFToInteger(_col3) (type: int) + expressions: UDFToInteger($f0) (type: int), $f1 (type: int), $f2 (type: string), UDFToInteger($f3) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2084,12 +2084,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string), (UDFToDouble(key) + 1.0) (type: double) - outputColumnNames: _col0, _col1 + expressions: key (type: string), (UDFToDouble(key) + 1.0) (type: double), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: double) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -2153,17 +2153,17 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: double) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) + expressions: UDFToInteger($f0) (type: int), UDFToInteger($f1) (type: int), UDFToInteger($f2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2337,26 +2337,26 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: subq1:t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(_col0) + UDFToDouble(_col0)) (type: double), _col1 (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: double) + aggregations: sum($f1) + keys: $f0 (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -2420,17 +2420,17 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:$hdt$_0:t1] + /t1 [subq1:t1] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: double) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) + expressions: UDFToInteger($f0) (type: int), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2510,8 +2510,8 @@ group by key + key POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ] -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)subq1:t1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)subq1:t1.FieldSchema(name:key, type:string, comment:null), ] PREHOOK: query: SELECT * FROM outputTbl1 PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl1 @@ -2615,107 +2615,115 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: null-subquery1:subq1-subquery1:t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Union Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: UDFToInteger($f0) (type: int), UDFToInteger($f1) (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,cnt + columns.comments + columns.types int:int #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE true - bucket_count -1 - columns key,cnt - columns.comments - columns.types int:int -#### A masked pattern was here #### - name default.outputtbl1 - numFiles 1 - numRows 5 - rawDataSize 17 - serialization.ddl struct outputtbl1 { i32 key, i32 cnt} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 22 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false + name default.outputtbl1 + numFiles 1 + numRows 5 + rawDataSize 17 + serialization.ddl struct outputtbl1 { i32 key, i32 cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 22 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false TableScan - alias: t1 + alias: null-subquery2:subq1-subquery2:t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Union Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: UDFToInteger($f0) (type: int), UDFToInteger($f1) (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,cnt + columns.comments + columns.types int:int +#### A masked pattern was here #### + name default.outputtbl1 + numFiles 1 + numRows 5 + rawDataSize 17 + serialization.ddl struct outputtbl1 { i32 key, i32 cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 22 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE true - bucket_count -1 - columns key,cnt - columns.comments - columns.types int:int -#### A masked pattern was here #### - name default.outputtbl1 - numFiles 1 - numRows 5 - rawDataSize 17 - serialization.ddl struct outputtbl1 { i32 key, i32 cnt} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 22 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -2768,7 +2776,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [null-subquery1:$hdt$_0-subquery1:$hdt$_0:t1, null-subquery2:$hdt$_0-subquery2:$hdt$_0:t1] + /t1 [null-subquery1:subq1-subquery1:t1, null-subquery2:subq1-subquery2:t1] Stage: Stage-7 Conditional Operator @@ -3002,8 +3010,8 @@ SELECT key, count(1) FROM T1 GROUP BY key POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ] -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)null-subquery1:subq1-subquery1:t1.null, (t1)null-subquery2:subq1-subquery2:t1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)null-subquery1:subq1-subquery1:t1.FieldSchema(name:key, type:string, comment:null), (t1)null-subquery2:subq1-subquery2:t1.FieldSchema(name:key, type:string, comment:null), ] PREHOOK: query: SELECT * FROM outputTbl1 PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl1 @@ -3120,16 +3128,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: null-subquery2:subq1-subquery2:t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: (UDFToDouble(key) + UDFToDouble(key)) (type: double) - outputColumnNames: _col0 + expressions: (UDFToDouble(key) + UDFToDouble(key)) (type: double), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: double) + aggregations: count($f1) + keys: $f0 (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -3193,58 +3201,62 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:t1] + /t1 [null-subquery2:subq1-subquery2:t1] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: double) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1 - columns.types double,bigint - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: $f0 (type: double), $f1 (type: bigint) + outputColumnNames: key, _o__c1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns key,_o__c1 + columns.types double,bigint + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: null-subquery1:subq1-subquery1:t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(_col0) (type: double), _col1 (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: key, _o__c1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) + expressions: UDFToInteger(key) (type: int), UDFToInteger(_o__c1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -3283,7 +3295,7 @@ STAGE PLANS: Union Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) + expressions: UDFToInteger(key) (type: int), UDFToInteger(_o__c1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -3326,7 +3338,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1 + columns key,_o__c1 columns.types double,bigint escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -3335,7 +3347,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1 + columns key,_o__c1 columns.types double,bigint escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -3389,7 +3401,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [null-subquery1:$hdt$_0-subquery1:$hdt$_0:t1] + /t1 [null-subquery1:subq1-subquery1:t1] #### A masked pattern was here #### Stage: Stage-8 @@ -3624,8 +3636,8 @@ SELECT key + key as key, count(1) as cnt FROM T1 GROUP BY key + key POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ] -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)null-subquery1:subq1-subquery1:t1.null, (t1)null-subquery2:subq1-subquery2:t1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)null-subquery1:subq1-subquery1:t1.FieldSchema(name:key, type:string, comment:null), (t1)null-subquery2:subq1-subquery2:t1.FieldSchema(name:key, type:string, comment:null), ] PREHOOK: query: SELECT * FROM outputTbl1 PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl1 @@ -3762,20 +3774,28 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: key (type: string) - mode: final - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + keys: key (type: string) + mode: final + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: _col1 (type: bigint) - auto parallelism: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: bigint) + auto parallelism: false TableScan alias: t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -3784,20 +3804,28 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: key (type: string) - mode: final - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + keys: key (type: string) + mode: final + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: _col1 (type: bigint) - auto parallelism: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + tag: 1 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -4066,20 +4094,24 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: key (type: string), val (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: key, val Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Group By Operator + aggregations: count(1) + keys: key (type: string), val (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col2 (type: bigint) - auto parallelism: false + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col2 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -4141,23 +4173,27 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types string,string,bigint - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types string,string,bigint + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Map Reduce @@ -4170,20 +4206,28 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: key (type: string) - mode: final - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + keys: key (type: string) + mode: final + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: _col1 (type: bigint) - auto parallelism: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: bigint) + auto parallelism: false TableScan GatherStats: false Reduce Output Operator @@ -4278,27 +4322,31 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: string), _col4 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2,_col3,_col4 - columns.types string:bigint:string:string:bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2,_col3,_col4 + columns.types string:bigint:string:string:bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -4377,13 +4425,13 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f1) bucketGroup: true - keys: _col0 (type: string) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -4447,17 +4495,17 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) + expressions: UDFToInteger($f0) (type: int), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -4612,12 +4660,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + expressions: key (type: string), 1 (type: int), val (type: string) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), 1 (type: int), _col2 (type: string) + aggregations: count($f1) + keys: $f0 (type: string), $f1 (type: int), $f2 (type: string) mode: final outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -4708,7 +4756,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-7 Conditional Operator @@ -5027,12 +5075,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + expressions: key (type: string), 1 (type: int), val (type: string), 2 (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), 1 (type: int), _col2 (type: string), 2 (type: int) + aggregations: count($f1) + keys: $f0 (type: string), $f1 (type: int), $f2 (type: string), $f3 (type: int) mode: final outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -5118,7 +5166,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-7 Conditional Operator @@ -5412,16 +5460,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t2 + alias: subq:t2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + expressions: key (type: string), 1 (type: int), val (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), 1 (type: int), _col2 (type: string) + aggregations: count($f3) + keys: $f0 (type: string), $f1 (type: int), $f2 (type: string) mode: final outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -5512,7 +5560,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [subq:t2] Stage: Stage-7 Conditional Operator @@ -5742,10 +5790,10 @@ group by key, constant, val POSTHOOK: type: QUERY POSTHOOK: Input: default@t2 POSTHOOK: Output: default@outputtbl4 -POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t2)t2.null, ] -POSTHOOK: Lineage: outputtbl4.key1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t2)subq:t2.null, ] +POSTHOOK: Lineage: outputtbl4.key1 EXPRESSION [(t2)subq:t2.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl4.key2 SIMPLE [] -POSTHOOK: Lineage: outputtbl4.key3 SIMPLE [(t2)t2.FieldSchema(name:val, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl4.key3 SIMPLE [(t2)subq:t2.FieldSchema(name:val, type:string, comment:null), ] PREHOOK: query: SELECT * FROM outputTbl4 PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl4 @@ -5870,16 +5918,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t2 + alias: subq2:subq:t2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + expressions: key (type: string), 2 (type: int), val (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), 2 (type: int), _col2 (type: string) + aggregations: count($f3) + keys: $f0 (type: string), $f1 (type: int), $f2 (type: string) mode: final outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -5970,7 +6018,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [subq2:subq:t2] Stage: Stage-7 Conditional Operator @@ -6206,10 +6254,10 @@ group by key, constant3, val POSTHOOK: type: QUERY POSTHOOK: Input: default@t2 POSTHOOK: Output: default@outputtbl4 -POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t2)t2.null, ] -POSTHOOK: Lineage: outputtbl4.key1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t2)subq2:subq:t2.null, ] +POSTHOOK: Lineage: outputtbl4.key1 EXPRESSION [(t2)subq2:subq:t2.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl4.key2 SIMPLE [] -POSTHOOK: Lineage: outputtbl4.key3 SIMPLE [(t2)t2.FieldSchema(name:val, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl4.key3 SIMPLE [(t2)subq2:subq:t2.FieldSchema(name:val, type:string, comment:null), ] PREHOOK: query: SELECT * FROM outputTbl4 PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl4 diff --git a/ql/src/test/results/clientpositive/groupby_sort_2.q.out b/ql/src/test/results/clientpositive/groupby_sort_2.q.out index b5e52f1..aa518ea 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_2.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_2.q.out @@ -65,13 +65,13 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: val (type: string) - outputColumnNames: _col0 + expressions: val (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f1) bucketGroup: true - keys: _col0 (type: string) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -86,10 +86,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + expressions: $f0 (type: string), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/groupby_sort_3.q.out b/ql/src/test/results/clientpositive/groupby_sort_3.q.out index c16911a..c2a1d44 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_3.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_3.q.out @@ -68,12 +68,12 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), val (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -205,12 +205,12 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/groupby_sort_4.q.out b/ql/src/test/results/clientpositive/groupby_sort_4.q.out index a6b1c3d..dfa4209 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_4.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_4.q.out @@ -65,13 +65,13 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f1) bucketGroup: true - keys: _col0 (type: string) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -86,10 +86,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + expressions: $f0 (type: string), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -172,12 +172,12 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), val (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -192,10 +192,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col2) (type: int) + expressions: $f0 (type: string), $f1 (type: string), UDFToInteger($f2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/groupby_sort_5.q.out b/ql/src/test/results/clientpositive/groupby_sort_5.q.out index 369e2b5..5bd3433 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_5.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_5.q.out @@ -72,12 +72,12 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), val (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -243,12 +243,12 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), val (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -419,13 +419,13 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f1) bucketGroup: true - keys: _col0 (type: string) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -440,10 +440,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + expressions: $f0 (type: string), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/groupby_sort_6.q.out b/ql/src/test/results/clientpositive/groupby_sort_6.q.out index 0169430..4fb66a2 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_6.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_6.q.out @@ -76,12 +76,12 @@ STAGE PLANS: predicate: (ds = '1') (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -99,10 +99,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) + expressions: UDFToInteger($f0) (type: int), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator @@ -245,12 +245,12 @@ STAGE PLANS: predicate: (ds = '1') (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -268,10 +268,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) + expressions: UDFToInteger($f0) (type: int), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator @@ -413,12 +413,12 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: PARTIAL Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -479,17 +479,17 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1/ds=2 [$hdt$_0:t1] + /t1/ds=2 [t1] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) + expressions: UDFToInteger($f0) (type: int), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/groupby_sort_7.q.out b/ql/src/test/results/clientpositive/groupby_sort_7.q.out index 7264695..e58006f 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_7.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_7.q.out @@ -75,12 +75,12 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), val (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/groupby_sort_8.q.out b/ql/src/test/results/clientpositive/groupby_sort_8.q.out index ec16eb0..af213c1 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_8.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_8.q.out @@ -56,12 +56,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0) + aggregations: count(DISTINCT key) bucketGroup: true - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -74,15 +74,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -122,11 +126,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0) - keys: _col0 (type: string) + aggregations: count(DISTINCT key) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -138,15 +142,19 @@ STAGE PLANS: Group By Operator aggregations: count(DISTINCT KEY._col0:0._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/groupby_sort_9.q.out b/ql/src/test/results/clientpositive/groupby_sort_9.q.out index e49781a..d69b5c4 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_9.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_9.q.out @@ -65,13 +65,13 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f1) bucketGroup: true - keys: _col0 (type: string) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: NONE @@ -86,15 +86,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/groupby_sort_skew_1_23.q.out b/ql/src/test/results/clientpositive/groupby_sort_skew_1_23.q.out index 2a956fc..13e4e23 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_skew_1_23.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_skew_1_23.q.out @@ -98,12 +98,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -189,7 +189,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-7 Conditional Operator @@ -458,12 +458,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), val (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -527,7 +527,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -598,10 +598,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: final - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) + expressions: UDFToInteger($f0) (type: int), $f1 (type: string), UDFToInteger($f2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -749,16 +749,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: subq1:t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -849,7 +849,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [subq1:t1] Stage: Stage-7 Conditional Operator @@ -1075,8 +1075,8 @@ SELECT key, count(1) FROM (SELECT key, val FROM T1) subq1 GROUP BY key POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ] -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)subq1:t1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)subq1:t1.FieldSchema(name:key, type:string, comment:null), ] PREHOOK: query: SELECT * FROM outputTbl1 PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl1 @@ -1157,16 +1157,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: subq1:t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1257,7 +1257,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [subq1:t1] Stage: Stage-7 Conditional Operator @@ -1483,8 +1483,8 @@ SELECT k, count(1) FROM (SELECT key as k, val as v FROM T1) subq1 GROUP BY k POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ] -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)subq1:t1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)subq1:t1.FieldSchema(name:key, type:string, comment:null), ] PREHOOK: query: SELECT * FROM outputTbl1 PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl1 @@ -1565,12 +1565,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col1 + expressions: 1 (type: int), key (type: string) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: 1 (type: int), _col1 (type: string) + aggregations: count($f0) + keys: $f0 (type: int), $f1 (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1656,7 +1656,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-7 Conditional Operator @@ -1929,12 +1929,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + expressions: key (type: string), 1 (type: int), val (type: string) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), 1 (type: int), _col2 (type: string) + aggregations: count($f1) + keys: $f0 (type: string), $f1 (type: int), $f2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -1998,7 +1998,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -2069,10 +2069,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string) mode: final - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: int), _col2 (type: string), UDFToInteger(_col3) (type: int) + expressions: UDFToInteger($f0) (type: int), $f1 (type: int), $f2 (type: string), UDFToInteger($f3) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2215,12 +2215,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string), (UDFToDouble(key) + 1.0) (type: double) - outputColumnNames: _col0, _col1 + expressions: key (type: string), (UDFToDouble(key) + 1.0) (type: double), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: double) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -2284,7 +2284,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -2355,10 +2355,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: double) mode: final - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) + expressions: UDFToInteger($f0) (type: int), UDFToInteger($f1) (type: int), UDFToInteger($f2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2533,26 +2533,26 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: subq1:t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(_col0) + UDFToDouble(_col0)) (type: double), _col1 (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: double) + aggregations: sum($f1) + keys: $f0 (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -2616,7 +2616,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:$hdt$_0:t1] + /t1 [subq1:t1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -2687,10 +2687,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: double) mode: final - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) + expressions: UDFToInteger($f0) (type: int), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2770,8 +2770,8 @@ group by key + key POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ] -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)subq1:t1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)subq1:t1.FieldSchema(name:key, type:string, comment:null), ] PREHOOK: query: SELECT * FROM outputTbl1 PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl1 @@ -2875,107 +2875,115 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: null-subquery1:subq1-subquery1:t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Union Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: UDFToInteger($f0) (type: int), UDFToInteger($f1) (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,cnt + columns.comments + columns.types int:int +#### A masked pattern was here #### + name default.outputtbl1 + numFiles 1 + numRows 5 + rawDataSize 17 + serialization.ddl struct outputtbl1 { i32 key, i32 cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 22 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE true - bucket_count -1 - columns key,cnt - columns.comments - columns.types int:int -#### A masked pattern was here #### - name default.outputtbl1 - numFiles 1 - numRows 5 - rawDataSize 17 - serialization.ddl struct outputtbl1 { i32 key, i32 cnt} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 22 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false TableScan - alias: t1 + alias: null-subquery2:subq1-subquery2:t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Union Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: UDFToInteger($f0) (type: int), UDFToInteger($f1) (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 1 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE true - bucket_count -1 - columns key,cnt - columns.comments - columns.types int:int -#### A masked pattern was here #### - name default.outputtbl1 - numFiles 1 - numRows 5 - rawDataSize 17 - serialization.ddl struct outputtbl1 { i32 key, i32 cnt} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 22 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,cnt + columns.comments + columns.types int:int +#### A masked pattern was here #### + name default.outputtbl1 + numFiles 1 + numRows 5 + rawDataSize 17 + serialization.ddl struct outputtbl1 { i32 key, i32 cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 22 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -3028,7 +3036,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [null-subquery1:$hdt$_0-subquery1:$hdt$_0:t1, null-subquery2:$hdt$_0-subquery2:$hdt$_0:t1] + /t1 [null-subquery1:subq1-subquery1:t1, null-subquery2:subq1-subquery2:t1] Stage: Stage-7 Conditional Operator @@ -3262,8 +3270,8 @@ SELECT key, count(1) FROM T1 GROUP BY key POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ] -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)null-subquery1:subq1-subquery1:t1.null, (t1)null-subquery2:subq1-subquery2:t1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)null-subquery1:subq1-subquery1:t1.FieldSchema(name:key, type:string, comment:null), (t1)null-subquery2:subq1-subquery2:t1.FieldSchema(name:key, type:string, comment:null), ] PREHOOK: query: SELECT * FROM outputTbl1 PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl1 @@ -3381,16 +3389,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: null-subquery2:subq1-subquery2:t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: (UDFToDouble(key) + UDFToDouble(key)) (type: double) - outputColumnNames: _col0 + expressions: (UDFToDouble(key) + UDFToDouble(key)) (type: double), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: double) + aggregations: count($f1) + keys: $f0 (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -3454,7 +3462,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:t1] + /t1 [null-subquery2:subq1-subquery2:t1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -3525,51 +3533,55 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: double) mode: final - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + Select Operator + expressions: $f0 (type: double), $f1 (type: bigint) + outputColumnNames: key, _o__c1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1 - columns.types double,bigint - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns key,_o__c1 + columns.types double,bigint + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: null-subquery1:subq1-subquery1:t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(_col0) (type: double), _col1 (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: key, _o__c1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) + expressions: UDFToInteger(key) (type: int), UDFToInteger(_o__c1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -3608,7 +3620,7 @@ STAGE PLANS: Union Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) + expressions: UDFToInteger(key) (type: int), UDFToInteger(_o__c1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -3651,7 +3663,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1 + columns key,_o__c1 columns.types double,bigint escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -3660,7 +3672,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1 + columns key,_o__c1 columns.types double,bigint escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -3714,7 +3726,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [null-subquery1:$hdt$_0-subquery1:$hdt$_0:t1] + /t1 [null-subquery1:subq1-subquery1:t1] #### A masked pattern was here #### Stage: Stage-8 @@ -3949,8 +3961,8 @@ SELECT key + key as key, count(1) as cnt FROM T1 GROUP BY key + key POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ] -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)null-subquery1:subq1-subquery1:t1.null, (t1)null-subquery2:subq1-subquery2:t1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(t1)null-subquery1:subq1-subquery1:t1.FieldSchema(name:key, type:string, comment:null), (t1)null-subquery2:subq1-subquery2:t1.FieldSchema(name:key, type:string, comment:null), ] PREHOOK: query: SELECT * FROM outputTbl1 PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl1 @@ -4087,20 +4099,28 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: key (type: string) - mode: final - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + keys: key (type: string) + mode: final + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: _col1 (type: bigint) - auto parallelism: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: bigint) + auto parallelism: false TableScan alias: t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -4109,20 +4129,28 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: key (type: string) - mode: final - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + keys: key (type: string) + mode: final + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: _col1 (type: bigint) - auto parallelism: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + tag: 1 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -4392,20 +4420,24 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: key (type: string), val (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: key, val Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: rand() (type: double) + Group By Operator + aggregations: count(1) + keys: key (type: string), val (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col2 (type: bigint) - auto parallelism: false + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: rand() (type: double) + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col2 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -4531,23 +4563,27 @@ STAGE PLANS: mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types string,string,bigint - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types string,string,bigint + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Map Reduce @@ -4560,20 +4596,28 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: key (type: string) - mode: final - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + keys: key (type: string) + mode: final + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: _col1 (type: bigint) - auto parallelism: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: _col1 (type: bigint) + auto parallelism: false TableScan GatherStats: false Reduce Output Operator @@ -4668,27 +4712,31 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: string), _col4 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2,_col3,_col4 - columns.types string:bigint:string:string:bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2,_col3,_col4 + columns.types string:bigint:string:string:bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -4768,13 +4816,13 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f1) bucketGroup: true - keys: _col0 (type: string) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -4838,7 +4886,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -4909,10 +4957,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) + expressions: UDFToInteger($f0) (type: int), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -5067,12 +5115,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + expressions: key (type: string), 1 (type: int), val (type: string) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), 1 (type: int), _col2 (type: string) + aggregations: count($f1) + keys: $f0 (type: string), $f1 (type: int), $f2 (type: string) mode: final outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -5163,7 +5211,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-7 Conditional Operator @@ -5482,12 +5530,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + expressions: key (type: string), 1 (type: int), val (type: string), 2 (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), 1 (type: int), _col2 (type: string), 2 (type: int) + aggregations: count($f1) + keys: $f0 (type: string), $f1 (type: int), $f2 (type: string), $f3 (type: int) mode: final outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -5573,7 +5621,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-7 Conditional Operator @@ -5867,16 +5915,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t2 + alias: subq:t2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + expressions: key (type: string), 1 (type: int), val (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), 1 (type: int), _col2 (type: string) + aggregations: count($f3) + keys: $f0 (type: string), $f1 (type: int), $f2 (type: string) mode: final outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -5967,7 +6015,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [subq:t2] Stage: Stage-7 Conditional Operator @@ -6197,10 +6245,10 @@ group by key, constant, val POSTHOOK: type: QUERY POSTHOOK: Input: default@t2 POSTHOOK: Output: default@outputtbl4 -POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t2)t2.null, ] -POSTHOOK: Lineage: outputtbl4.key1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t2)subq:t2.null, ] +POSTHOOK: Lineage: outputtbl4.key1 EXPRESSION [(t2)subq:t2.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl4.key2 SIMPLE [] -POSTHOOK: Lineage: outputtbl4.key3 SIMPLE [(t2)t2.FieldSchema(name:val, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl4.key3 SIMPLE [(t2)subq:t2.FieldSchema(name:val, type:string, comment:null), ] PREHOOK: query: SELECT * FROM outputTbl4 PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl4 @@ -6325,16 +6373,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t2 + alias: subq2:subq:t2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + expressions: key (type: string), 2 (type: int), val (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), 2 (type: int), _col2 (type: string) + aggregations: count($f3) + keys: $f0 (type: string), $f1 (type: int), $f2 (type: string) mode: final outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -6425,7 +6473,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [subq2:subq:t2] Stage: Stage-7 Conditional Operator @@ -6661,10 +6709,10 @@ group by key, constant3, val POSTHOOK: type: QUERY POSTHOOK: Input: default@t2 POSTHOOK: Output: default@outputtbl4 -POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t2)t2.null, ] -POSTHOOK: Lineage: outputtbl4.key1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl4.cnt EXPRESSION [(t2)subq2:subq:t2.null, ] +POSTHOOK: Lineage: outputtbl4.key1 EXPRESSION [(t2)subq2:subq:t2.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl4.key2 SIMPLE [] -POSTHOOK: Lineage: outputtbl4.key3 SIMPLE [(t2)t2.FieldSchema(name:val, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl4.key3 SIMPLE [(t2)subq2:subq:t2.FieldSchema(name:val, type:string, comment:null), ] PREHOOK: query: SELECT * FROM outputTbl4 PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl4 diff --git a/ql/src/test/results/clientpositive/groupby_sort_test_1.q.out b/ql/src/test/results/clientpositive/groupby_sort_test_1.q.out index 8c1765d..f2f4eb3 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_test_1.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_test_1.q.out @@ -61,12 +61,12 @@ STAGE PLANS: alias: t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -81,10 +81,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) + expressions: UDFToInteger($f0) (type: int), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/having.q.out b/ql/src/test/results/clientpositive/having.q.out index 8682a46..14e370b 100644 --- a/ql/src/test/results/clientpositive/having.q.out +++ b/ql/src/test/results/clientpositive/having.q.out @@ -101,11 +101,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) + aggregations: max(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -120,15 +120,19 @@ STAGE PLANS: aggregations: max(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: string) + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -469,11 +473,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) + aggregations: max(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -488,14 +492,14 @@ STAGE PLANS: aggregations: max(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col1 > 'val_255') (type: boolean) + predicate: ($f1 > 'val_255') (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -738,11 +742,11 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) + aggregations: max(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -757,14 +761,14 @@ STAGE PLANS: aggregations: max(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col1 > 'val_255') (type: boolean) + predicate: ($f1 > 'val_255') (type: boolean) Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -930,11 +934,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) + aggregations: max(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -949,18 +953,22 @@ STAGE PLANS: aggregations: max(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col1 > 'val_255') (type: boolean) + predicate: ($f1 > 'val_255') (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: string) + outputColumnNames: key, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1192,11 +1200,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1211,18 +1219,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col1 >= 4) (type: boolean) + predicate: ($f1 >= 4) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/having2.q.out b/ql/src/test/results/clientpositive/having2.q.out index ba601f9..5582de2 100644 --- a/ql/src/test/results/clientpositive/having2.q.out +++ b/ql/src/test/results/clientpositive/having2.q.out @@ -133,11 +133,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: customer_name (type: string), customer_balance (type: double), order_quantity (type: double), discount (type: double) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: sum(_col1), sum(_col2), count(_col3) - keys: _col0 (type: string) + aggregations: sum($f1), sum($f2), count($f3) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -152,14 +152,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), sum(VALUE._col1), count(VALUE._col2) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((_col3 <= 822) and (_col1 <= 4074689.000000041)) (type: boolean) + predicate: (($f3 <= 822) and ($f1 <= 4074689.000000041)) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: double) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f1 (type: double), $f2 (type: double) + outputColumnNames: customer_name, _o__c1, _o__c2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false @@ -200,11 +200,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: customer_name (type: string), customer_balance (type: double), order_quantity (type: double), discount (type: double) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: sum(_col1), sum(_col2), count(_col3) - keys: _col0 (type: string) + aggregations: sum($f1), sum($f2), count($f3) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -219,14 +219,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), sum(VALUE._col1), count(VALUE._col2) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((_col1 <= 4074689.000000041) and (_col3 <= 822)) (type: boolean) + predicate: (($f1 <= 4074689.000000041) and ($f3 <= 822)) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: double) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f1 (type: double), $f2 (type: double) + outputColumnNames: customer_name, _o__c1, _o__c2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/implicit_cast1.q.out b/ql/src/test/results/clientpositive/implicit_cast1.q.out index 1a12a6c..b5db4d1 100644 --- a/ql/src/test/results/clientpositive/implicit_cast1.q.out +++ b/ql/src/test/results/clientpositive/implicit_cast1.q.out @@ -32,7 +32,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: a (type: bigint), b (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/index_auto.q.out b/ql/src/test/results/clientpositive/index_auto.q.out index 28f1e96..85b33cf 100644 --- a/ql/src/test/results/clientpositive/index_auto.q.out +++ b/ql/src/test/results/clientpositive/index_auto.q.out @@ -81,7 +81,7 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -152,7 +152,7 @@ STAGE PLANS: predicate: ((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -187,7 +187,7 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/index_auto_empty.q.out b/ql/src/test/results/clientpositive/index_auto_empty.q.out index 0923856..4fe8a6c 100644 --- a/ql/src/test/results/clientpositive/index_auto_empty.q.out +++ b/ql/src/test/results/clientpositive/index_auto_empty.q.out @@ -69,7 +69,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: '86' (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/index_auto_file_format.q.out b/ql/src/test/results/clientpositive/index_auto_file_format.q.out index 8f62188..e296ba1 100644 --- a/ql/src/test/results/clientpositive/index_auto_file_format.q.out +++ b/ql/src/test/results/clientpositive/index_auto_file_format.q.out @@ -46,7 +46,7 @@ STAGE PLANS: predicate: (UDFToDouble(key) = 86.0) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -81,7 +81,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '86' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -162,7 +162,7 @@ STAGE PLANS: predicate: (UDFToDouble(key) = 86.0) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -197,7 +197,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '86' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/index_auto_mult_tables.q.out b/ql/src/test/results/clientpositive/index_auto_mult_tables.q.out index 7755ed5..a64acba 100644 --- a/ql/src/test/results/clientpositive/index_auto_mult_tables.q.out +++ b/ql/src/test/results/clientpositive/index_auto_mult_tables.q.out @@ -19,52 +19,52 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) and key is not null) (type: boolean) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + predicate: ((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) TableScan - alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: b + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) (type: boolean) + Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value + Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -223,16 +223,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: default__srcpart_srcpart_index__ - filterExpr: (((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) + alias: tmp_index:ind0:default__src_src_index__ + filterExpr: (((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Filter Operator - predicate: (((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) + predicate: (((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Select Operator expressions: _bucketname (type: string), _offset (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: bucketname, offset Group By Operator - aggregations: collect_set(_col1) - keys: _col0 (type: string) + aggregations: collect_set(offset) + keys: bucketname (type: string) mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator @@ -245,13 +245,16 @@ STAGE PLANS: aggregations: collect_set(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: bucketname, $f1 + Select Operator + expressions: bucketname (type: string), $f1 (type: array) + outputColumnNames: bucketname, $f1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Move Operator @@ -263,54 +266,54 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b - filterExpr: (((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) and key is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + alias: a + filterExpr: ((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) and key is not null) (type: boolean) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + predicate: ((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) TableScan - alias: a - filterExpr: (((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: b + filterExpr: ((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) (type: boolean) + Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value + Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -320,16 +323,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: default__src_src_index__ - filterExpr: (((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) + alias: tmp_index:ind0:default__srcpart_srcpart_index__ + filterExpr: (((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Filter Operator - predicate: (((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) + predicate: (((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Select Operator expressions: _bucketname (type: string), _offset (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: bucketname, offset Group By Operator - aggregations: collect_set(_col1) - keys: _col0 (type: string) + aggregations: collect_set(offset) + keys: bucketname (type: string) mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator @@ -342,13 +345,16 @@ STAGE PLANS: aggregations: collect_set(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: bucketname, $f1 + Select Operator + expressions: bucketname (type: string), $f1 (type: array) + outputColumnNames: bucketname, $f1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-5 Move Operator diff --git a/ql/src/test/results/clientpositive/index_auto_mult_tables_compact.q.out b/ql/src/test/results/clientpositive/index_auto_mult_tables_compact.q.out index 1aa82ba..40135bf 100644 --- a/ql/src/test/results/clientpositive/index_auto_mult_tables_compact.q.out +++ b/ql/src/test/results/clientpositive/index_auto_mult_tables_compact.q.out @@ -19,52 +19,52 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) and key is not null) (type: boolean) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + predicate: ((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) TableScan - alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: b + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) (type: boolean) + Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value + Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -230,13 +230,13 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: default__srcpart_srcpart_index__ - filterExpr: ((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) (type: boolean) + alias: default__src_src_index__ + filterExpr: ((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) (type: boolean) Filter Operator - predicate: ((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) (type: boolean) + predicate: ((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -263,54 +263,54 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b - filterExpr: (((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) and key is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + alias: a + filterExpr: ((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) and key is not null) (type: boolean) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + predicate: ((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) TableScan - alias: a - filterExpr: (((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: b + filterExpr: ((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) (type: boolean) + Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value + Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -348,13 +348,13 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: default__src_src_index__ - filterExpr: ((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) (type: boolean) + alias: default__srcpart_srcpart_index__ + filterExpr: ((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) (type: boolean) Filter Operator - predicate: ((((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) (type: boolean) + predicate: ((((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/index_auto_multiple.q.out b/ql/src/test/results/clientpositive/index_auto_multiple.q.out index d56cd34..6fb265d 100644 --- a/ql/src/test/results/clientpositive/index_auto_multiple.q.out +++ b/ql/src/test/results/clientpositive/index_auto_multiple.q.out @@ -66,7 +66,7 @@ STAGE PLANS: predicate: (UDFToDouble(key) = 86.0) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -101,7 +101,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '86' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/index_auto_partitioned.q.out b/ql/src/test/results/clientpositive/index_auto_partitioned.q.out index a572471..b8811d6 100644 --- a/ql/src/test/results/clientpositive/index_auto_partitioned.q.out +++ b/ql/src/test/results/clientpositive/index_auto_partitioned.q.out @@ -69,7 +69,7 @@ STAGE PLANS: predicate: (UDFToDouble(key) = 86.0) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -104,7 +104,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '86' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/index_auto_self_join.q.out b/ql/src/test/results/clientpositive/index_auto_self_join.q.out index a214845..1c4fdb7 100644 --- a/ql/src/test/results/clientpositive/index_auto_self_join.q.out +++ b/ql/src/test/results/clientpositive/index_auto_self_join.q.out @@ -20,50 +20,50 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and value is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((value is not null and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) (type: boolean) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and value is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((value is not null and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) (type: boolean) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key, key0 + Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), key0 (type: string) + outputColumnNames: key, key1 + Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -131,16 +131,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: default__src_src_index__ + alias: tmp_index:ind0:default__src_src_index__ filterExpr: (((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Filter Operator predicate: (((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Select Operator expressions: _bucketname (type: string), _offset (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: bucketname, offset Group By Operator - aggregations: collect_set(_col1) - keys: _col0 (type: string) + aggregations: collect_set(offset) + keys: bucketname (type: string) mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator @@ -153,13 +153,16 @@ STAGE PLANS: aggregations: collect_set(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: bucketname, $f1 + Select Operator + expressions: bucketname (type: string), $f1 (type: array) + outputColumnNames: bucketname, $f1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Move Operator @@ -172,54 +175,54 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - filterExpr: (((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and value is not null) (type: boolean) + filterExpr: ((value is not null and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and value is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((value is not null and (UDFToDouble(key) > 80.0)) and (UDFToDouble(key) < 100.0)) (type: boolean) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: string) TableScan - alias: a - filterExpr: (((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and value is not null) (type: boolean) + alias: b + filterExpr: ((value is not null and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and value is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((value is not null and (UDFToDouble(key) > 70.0)) and (UDFToDouble(key) < 90.0)) (type: boolean) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key, key0 + Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), key0 (type: string) + outputColumnNames: key, key1 + Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -229,16 +232,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: default__src_src_index__ + alias: tmp_index:ind0:default__src_src_index__ filterExpr: (((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Filter Operator predicate: (((UDFToDouble(key) > 70.0) and (UDFToDouble(key) < 90.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Select Operator expressions: _bucketname (type: string), _offset (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: bucketname, offset Group By Operator - aggregations: collect_set(_col1) - keys: _col0 (type: string) + aggregations: collect_set(offset) + keys: bucketname (type: string) mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator @@ -251,13 +254,16 @@ STAGE PLANS: aggregations: collect_set(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: bucketname, $f1 + Select Operator + expressions: bucketname (type: string), $f1 (type: array) + outputColumnNames: bucketname, $f1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-5 Move Operator diff --git a/ql/src/test/results/clientpositive/index_auto_unused.q.out b/ql/src/test/results/clientpositive/index_auto_unused.q.out index e1ddff8..8a6ebbf 100644 --- a/ql/src/test/results/clientpositive/index_auto_unused.q.out +++ b/ql/src/test/results/clientpositive/index_auto_unused.q.out @@ -45,7 +45,7 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -111,7 +111,7 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -177,7 +177,7 @@ STAGE PLANS: Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -280,7 +280,7 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -372,7 +372,7 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '2008-04-09' (type: string), '12' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/index_auto_update.q.out b/ql/src/test/results/clientpositive/index_auto_update.q.out index 70d0286..9975a89 100644 --- a/ql/src/test/results/clientpositive/index_auto_update.q.out +++ b/ql/src/test/results/clientpositive/index_auto_update.q.out @@ -72,7 +72,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -109,10 +109,10 @@ STAGE PLANS: alias: temp Select Operator expressions: key (type: string), INPUT__FILE__NAME (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Group By Operator - aggregations: collect_set(_col2) - keys: _col0 (type: string), _col1 (type: string) + aggregations: collect_set($f2) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Reduce Output Operator @@ -125,14 +125,17 @@ STAGE PLANS: aggregations: collect_set(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.default__temp_temp_index__ + outputColumnNames: $f0, $f1, $f2 + Select Operator + expressions: $f0 (type: string), $f1 (type: string), $f2 (type: array) + outputColumnNames: $f0, $f1, $f2 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.default__temp_temp_index__ Stage: Stage-1 Move Operator @@ -227,7 +230,7 @@ STAGE PLANS: predicate: (UDFToDouble(key) = 86.0) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -262,7 +265,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '86' (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/index_bitmap_auto_partitioned.q.out b/ql/src/test/results/clientpositive/index_bitmap_auto_partitioned.q.out index 65b6721..5e8c143 100644 --- a/ql/src/test/results/clientpositive/index_bitmap_auto_partitioned.q.out +++ b/ql/src/test/results/clientpositive/index_bitmap_auto_partitioned.q.out @@ -64,16 +64,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: default__srcpart_src_part_index__ + alias: tmp_index:ind0:default__srcpart_src_part_index__ filterExpr: ((UDFToDouble(key) = 86.0) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Filter Operator predicate: ((UDFToDouble(key) = 86.0) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Select Operator expressions: _bucketname (type: string), _offset (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: bucketname, offset Group By Operator - aggregations: collect_set(_col1) - keys: _col0 (type: string) + aggregations: collect_set(offset) + keys: bucketname (type: string) mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator @@ -86,13 +86,16 @@ STAGE PLANS: aggregations: collect_set(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: bucketname, $f1 + Select Operator + expressions: bucketname (type: string), $f1 (type: array) + outputColumnNames: bucketname, $f1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-2 Move Operator @@ -112,7 +115,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '86' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/index_bitmap_compression.q.out b/ql/src/test/results/clientpositive/index_bitmap_compression.q.out index 9673f08..7b88cce 100644 --- a/ql/src/test/results/clientpositive/index_bitmap_compression.q.out +++ b/ql/src/test/results/clientpositive/index_bitmap_compression.q.out @@ -38,16 +38,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: default__src_src_index__ + alias: tmp_index:ind0:default__src_src_index__ filterExpr: (((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Filter Operator predicate: (((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) and (not EWAH_BITMAP_EMPTY(_bitmaps))) (type: boolean) Select Operator expressions: _bucketname (type: string), _offset (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: bucketname, offset Group By Operator - aggregations: collect_set(_col1) - keys: _col0 (type: string) + aggregations: collect_set(offset) + keys: bucketname (type: string) mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator @@ -60,13 +60,16 @@ STAGE PLANS: aggregations: collect_set(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: bucketname, $f1 + Select Operator + expressions: bucketname (type: string), $f1 (type: array) + outputColumnNames: bucketname, $f1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-2 Move Operator @@ -86,7 +89,7 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: true diff --git a/ql/src/test/results/clientpositive/index_compression.q.out b/ql/src/test/results/clientpositive/index_compression.q.out index 2ce196b..ce517d6 100644 --- a/ql/src/test/results/clientpositive/index_compression.q.out +++ b/ql/src/test/results/clientpositive/index_compression.q.out @@ -48,7 +48,7 @@ STAGE PLANS: predicate: ((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -83,7 +83,7 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: true diff --git a/ql/src/test/results/clientpositive/index_serde.q.out b/ql/src/test/results/clientpositive/index_serde.q.out index 388645d..9582e44 100644 --- a/ql/src/test/results/clientpositive/index_serde.q.out +++ b/ql/src/test/results/clientpositive/index_serde.q.out @@ -140,7 +140,7 @@ STAGE PLANS: predicate: (number > 6) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -175,7 +175,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: number (type: int), first_name (type: string), last_name (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: number, first_name, last_name Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/index_skewtable.q.out b/ql/src/test/results/clientpositive/index_skewtable.q.out index 10a441d..14b8aa2 100644 --- a/ql/src/test/results/clientpositive/index_skewtable.q.out +++ b/ql/src/test/results/clientpositive/index_skewtable.q.out @@ -97,7 +97,7 @@ STAGE PLANS: predicate: (value > '15') (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -132,17 +132,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: value (type: string) sort order: + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + value expressions: key (type: string) Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 + expressions: VALUE.key (type: string), KEY.reducesinkkey0 (type: string) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/index_stale.q.out b/ql/src/test/results/clientpositive/index_stale.q.out index b8bcfd7..2d18a6d 100644 --- a/ql/src/test/results/clientpositive/index_stale.q.out +++ b/ql/src/test/results/clientpositive/index_stale.q.out @@ -75,7 +75,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '86' (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/index_stale_partitioned.q.out b/ql/src/test/results/clientpositive/index_stale_partitioned.q.out index c9ecdb2..c7bed70 100644 --- a/ql/src/test/results/clientpositive/index_stale_partitioned.q.out +++ b/ql/src/test/results/clientpositive/index_stale_partitioned.q.out @@ -96,7 +96,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '86' (type: string), val (type: string), 'bar' (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, val, foo Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort.q.out index 5d69e2f..bcfe5c6 100644 --- a/ql/src/test/results/clientpositive/infer_bucket_sort.q.out +++ b/ql/src/test/results/clientpositive/infer_bucket_sort.q.out @@ -290,7 +290,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_table@part=1 POSTHOOK: Lineage: test_table PARTITION(part=1).key SIMPLE [(src)a.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table PARTITION(part=1).value SIMPLE [(src)a.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: test_table PARTITION(part=1).value SIMPLE [(src)c.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: DESCRIBE FORMATTED test_table PARTITION (part = '1') PREHOOK: type: DESCTABLE PREHOOK: Input: default@test_table @@ -343,7 +343,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_table@part=1 POSTHOOK: Lineage: test_table PARTITION(part=1).key SIMPLE [(src)a.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table PARTITION(part=1).value SIMPLE [(src)a.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: test_table PARTITION(part=1).value SIMPLE [(src)c.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: DESCRIBE FORMATTED test_table PARTITION (part = '1') PREHOOK: type: DESCTABLE PREHOOK: Input: default@test_table @@ -379,8 +379,8 @@ InputFormat: org.apache.hadoop.mapred.TextInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat Compressed: No Num Buckets: 1 -Bucket Columns: [key] -Sort Columns: [Order(col:key, order:1)] +Bucket Columns: [value] +Sort Columns: [Order(col:value, order:1)] Storage Desc Params: serialization.format 1 PREHOOK: query: -- Test distribute by, should only be bucketed by key @@ -660,8 +660,8 @@ SELECT key, value from (SELECT a.key, b.value FROM src a JOIN src b ON (a.key = POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_table@part=1 -POSTHOOK: Lineage: test_table PARTITION(part=1).key SIMPLE [(src)a.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table PARTITION(part=1).value SIMPLE [(src)a.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: test_table PARTITION(part=1).key SIMPLE [(src)subq:a.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: test_table PARTITION(part=1).value SIMPLE [(src)subq:b.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: DESCRIBE FORMATTED test_table PARTITION (part = '1') PREHOOK: type: DESCTABLE PREHOOK: Input: default@test_table @@ -713,8 +713,8 @@ SELECT k, value FROM (SELECT a.key as k, b.value FROM src a JOIN src b ON (a.key POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_table@part=1 -POSTHOOK: Lineage: test_table PARTITION(part=1).key SIMPLE [(src)a.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table PARTITION(part=1).value SIMPLE [(src)a.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: test_table PARTITION(part=1).key SIMPLE [(src)subq:a.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: test_table PARTITION(part=1).value SIMPLE [(src)subq:b.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: DESCRIBE FORMATTED test_table PARTITION (part = '1') PREHOOK: type: DESCTABLE PREHOOK: Input: default@test_table @@ -766,8 +766,8 @@ SELECT key, cnt from (SELECT key, count(*) as cnt FROM src GROUP BY key) subq POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_table@part=1 -POSTHOOK: Lineage: test_table PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table PARTITION(part=1).value EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: test_table PARTITION(part=1).key SIMPLE [(src)subq:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: test_table PARTITION(part=1).value EXPRESSION [(src)subq:src.null, ] PREHOOK: query: DESCRIBE FORMATTED test_table PARTITION (part = '1') PREHOOK: type: DESCTABLE PREHOOK: Input: default@test_table @@ -819,8 +819,8 @@ SELECT k, cnt FROM (SELECT key as k, count(*) as cnt FROM src GROUP BY key) subq POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_table@part=1 -POSTHOOK: Lineage: test_table PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table PARTITION(part=1).value EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: test_table PARTITION(part=1).key SIMPLE [(src)subq:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: test_table PARTITION(part=1).value EXPRESSION [(src)subq:src.null, ] PREHOOK: query: DESCRIBE FORMATTED test_table PARTITION (part = '1') PREHOOK: type: DESCTABLE PREHOOK: Input: default@test_table @@ -872,8 +872,8 @@ SELECT key, value FROM (SELECT key, count(1) AS value FROM src group by key) a w POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_table@part=1 -POSTHOOK: Lineage: test_table PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table PARTITION(part=1).value EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: test_table PARTITION(part=1).key SIMPLE [(src)a:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: test_table PARTITION(part=1).value EXPRESSION [(src)a:src.null, ] PREHOOK: query: DESCRIBE FORMATTED test_table PARTITION (part = '1') PREHOOK: type: DESCTABLE PREHOOK: Input: default@test_table @@ -925,8 +925,8 @@ SELECT key, value + 1 FROM (SELECT key, count(1) AS value FROM src group by key) POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_table@part=1 -POSTHOOK: Lineage: test_table PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table PARTITION(part=1).value EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: test_table PARTITION(part=1).key SIMPLE [(src)a:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: test_table PARTITION(part=1).value EXPRESSION [(src)a:src.null, ] PREHOOK: query: DESCRIBE FORMATTED test_table PARTITION (part = '1') PREHOOK: type: DESCTABLE PREHOOK: Input: default@test_table @@ -1033,8 +1033,8 @@ SELECT count(1), value FROM (SELECT key, count(1) as value FROM src group by key POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_table@part=1 -POSTHOOK: Lineage: test_table PARTITION(part=1).key EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: test_table PARTITION(part=1).value EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: test_table PARTITION(part=1).key EXPRESSION [(src)a:src.null, ] +POSTHOOK: Lineage: test_table PARTITION(part=1).value EXPRESSION [(src)a:src.null, ] PREHOOK: query: DESCRIBE FORMATTED test_table PARTITION (part = '1') PREHOOK: type: DESCTABLE PREHOOK: Input: default@test_table @@ -1088,8 +1088,8 @@ SELECT value, key FROM (SELECT key, count(1) as value FROM src group by key) a POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_table@part=1 -POSTHOOK: Lineage: test_table PARTITION(part=1).key EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: test_table PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: test_table PARTITION(part=1).key EXPRESSION [(src)a:src.null, ] +POSTHOOK: Lineage: test_table PARTITION(part=1).value SIMPLE [(src)a:src.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: DESCRIBE FORMATTED test_table PARTITION (part = '1') PREHOOK: type: DESCTABLE PREHOOK: Input: default@test_table @@ -1300,8 +1300,8 @@ SELECT key, value FROM (SELECT concat(key, "a") AS key, value, count(*) FROM sr POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_table@part=1 -POSTHOOK: Lineage: test_table PARTITION(part=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: test_table PARTITION(part=1).key EXPRESSION [(src)a:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: test_table PARTITION(part=1).value SIMPLE [(src)a:src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: DESCRIBE FORMATTED test_table PARTITION (part = '1') PREHOOK: type: DESCTABLE PREHOOK: Input: default@test_table diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_convert_join.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_convert_join.q.out index d1a6789..9077915 100644 --- a/ql/src/test/results/clientpositive/infer_bucket_sort_convert_join.q.out +++ b/ql/src/test/results/clientpositive/infer_bucket_sort_convert_join.q.out @@ -27,7 +27,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_table@part=1 POSTHOOK: Lineage: test_table PARTITION(part=1).key SIMPLE [(src)a.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table PARTITION(part=1).value SIMPLE [(src)a.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: test_table PARTITION(part=1).value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: DESCRIBE FORMATTED test_table PARTITION (part = '1') PREHOOK: type: DESCTABLE PREHOOK: Input: default@test_table @@ -86,7 +86,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_table@part=1 POSTHOOK: Lineage: test_table PARTITION(part=1).key SIMPLE [(src)a.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table PARTITION(part=1).value SIMPLE [(src)a.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: test_table PARTITION(part=1).value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: DESCRIBE FORMATTED test_table PARTITION (part = '1') PREHOOK: type: DESCTABLE PREHOOK: Input: default@test_table diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out index a621be8..0631663 100644 --- a/ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out +++ b/ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out @@ -43,32 +43,31 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f1 (type: string), $f2 (type: bigint) + outputColumnNames: key, value, _o__c2 Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -142,9 +141,9 @@ SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe InputFormat: org.apache.hadoop.mapred.TextInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat Compressed: No -Num Buckets: 1 -Bucket Columns: [key, value] -Sort Columns: [Order(col:key, order:1), Order(col:value, order:1)] +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] Storage Desc Params: serialization.format 1 PREHOOK: query: -- Test rollup, should be bucketed and sorted on key, value, grouping_key @@ -227,32 +226,31 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f1 (type: string), $f2 (type: bigint) + outputColumnNames: key, value, _o__c2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -326,9 +324,9 @@ SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe InputFormat: org.apache.hadoop.mapred.TextInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat Compressed: No -Num Buckets: 1 -Bucket Columns: [key, value] -Sort Columns: [Order(col:key, order:1), Order(col:value, order:1)] +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] Storage Desc Params: serialization.format 1 PREHOOK: query: -- Test cube, should be bucketed and sorted on key, value, grouping_key @@ -411,32 +409,31 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), '0' (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f1 (type: string), $f2 (type: bigint) + outputColumnNames: key, value, _o__c2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -510,9 +507,9 @@ SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe InputFormat: org.apache.hadoop.mapred.TextInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat Compressed: No -Num Buckets: 1 -Bucket Columns: [key, value] -Sort Columns: [Order(col:key, order:1), Order(col:value, order:1)] +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] Storage Desc Params: serialization.format 1 PREHOOK: query: -- Test grouping sets, should be bucketed and sorted on key, value, grouping_key diff --git a/ql/src/test/results/clientpositive/infer_const_type.q.out b/ql/src/test/results/clientpositive/infer_const_type.q.out index 05c6a45..d0b32aa 100644 --- a/ql/src/test/results/clientpositive/infer_const_type.q.out +++ b/ql/src/test/results/clientpositive/infer_const_type.q.out @@ -63,7 +63,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 39 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 127 (type: tinyint), 32767 (type: smallint), 12345 (type: int), -12345 (type: bigint), 906.0 (type: float), -307.0 (type: double), '1234' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: ti, si, i, bi, fl, db, str Statistics: Num rows: 1 Data size: 39 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -141,7 +141,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 117 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ti (type: tinyint), si (type: smallint), i (type: int), bi (type: bigint), fl (type: float), db (type: double), str (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: ti, si, i, bi, fl, db, str Statistics: Num rows: 1 Data size: 117 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -206,7 +206,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 117 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ti (type: tinyint), si (type: smallint), i (type: int), bi (type: bigint), fl (type: float), db (type: double), str (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: ti, si, i, bi, fl, db, str Statistics: Num rows: 1 Data size: 117 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -263,7 +263,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 39 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ti (type: tinyint), si (type: smallint), i (type: int), bi (type: bigint), fl (type: float), db (type: double), '1.57' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: ti, si, i, bi, fl, db, str Statistics: Num rows: 1 Data size: 39 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/innerjoin.q.out b/ql/src/test/results/clientpositive/innerjoin.q.out index 91bb7b3..8c81b87 100644 --- a/ql/src/test/results/clientpositive/innerjoin.q.out +++ b/ql/src/test/results/clientpositive/innerjoin.q.out @@ -28,21 +28,21 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -51,24 +51,24 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col2) (type: int), _col1 (type: string) + expressions: UDFToInteger(key0) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -104,7 +104,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest_j1 POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest_j1.* FROM dest_j1 PREHOOK: type: QUERY PREHOOK: Input: default@dest_j1 @@ -1192,47 +1192,51 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: inner:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/input.q.out b/ql/src/test/results/clientpositive/input.q.out index 286cd19..8ce03d1 100644 --- a/ql/src/test/results/clientpositive/input.q.out +++ b/ql/src/test/results/clientpositive/input.q.out @@ -17,7 +17,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/input0.q.out b/ql/src/test/results/clientpositive/input0.q.out index 4d66253..95ec821 100644 --- a/ql/src/test/results/clientpositive/input0.q.out +++ b/ql/src/test/results/clientpositive/input0.q.out @@ -17,7 +17,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/input11_limit.q.out b/ql/src/test/results/clientpositive/input11_limit.q.out index f9ac14e..46529be 100644 --- a/ql/src/test/results/clientpositive/input11_limit.q.out +++ b/ql/src/test/results/clientpositive/input11_limit.q.out @@ -20,8 +20,13 @@ INSERT OVERWRITE TABLE dest1 SELECT src.key, src.value WHERE src.key < 100 LIMIT POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 @@ -35,35 +40,32 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: UDFToInteger(key) (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -78,6 +80,36 @@ STAGE PLANS: Stage: Stage-2 Stats-Aggr Operator + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT src.key, src.value WHERE src.key < 100 LIMIT 10 PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/input22.q.out b/ql/src/test/results/clientpositive/input22.q.out index eecbcd3..d09afdc 100644 --- a/ql/src/test/results/clientpositive/input22.q.out +++ b/ql/src/test/results/clientpositive/input22.q.out @@ -35,20 +35,20 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: input4 + alias: a:input4 Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 diff --git a/ql/src/test/results/clientpositive/input23.q.out b/ql/src/test/results/clientpositive/input23.q.out index 159b9c5..d970767 100644 --- a/ql/src/test/results/clientpositive/input23.q.out +++ b/ql/src/test/results/clientpositive/input23.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join JOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[8][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain extended select * from srcpart a join srcpart b where a.ds = '2008-04-08' and a.hr = '11' and b.ds = '2008-04-08' and b.hr = '14' limit 5 PREHOOK: type: QUERY @@ -71,16 +71,16 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col0 (type: string), _col1 (type: string) + value expressions: key (type: string), value (type: string), '2008-04-08' (type: string), '11' (type: string) auto parallelism: false TableScan - alias: a + alias: b Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator @@ -89,13 +89,13 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE tag: 1 - value expressions: _col0 (type: string), _col1 (type: string) + value expressions: key (type: string), value (type: string), '2008-04-08' (type: string), '14' (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -147,7 +147,7 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:a] + /srcpart/ds=2008-04-08/hr=11 [a] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -156,11 +156,11 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col4, _col5 + outputColumnNames: key, value, ds, hr, key0, value0, ds0, hr0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), '11' (type: string), _col4 (type: string), _col5 (type: string), '2008-04-08' (type: string), '14' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string), key0 (type: string), value0 (type: string), ds0 (type: string), hr0 (type: string) + outputColumnNames: key, value, ds, hr, key0, value0, ds0, hr0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 @@ -176,7 +176,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 + columns key,value,ds,hr,key0,value0,ds0,hr0 columns.types string:string:string:string:string:string:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -193,7 +193,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[8][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select * from srcpart a join srcpart b where a.ds = '2008-04-08' and a.hr = '11' and b.ds = '2008-04-08' and b.hr = '14' limit 5 PREHOOK: type: QUERY PREHOOK: Input: default@srcpart diff --git a/ql/src/test/results/clientpositive/input24.q.out b/ql/src/test/results/clientpositive/input24.q.out index d091ee8..8757f52 100644 --- a/ql/src/test/results/clientpositive/input24.q.out +++ b/ql/src/test/results/clientpositive/input24.q.out @@ -31,9 +31,11 @@ STAGE PLANS: alias: x Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -45,15 +47,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/input25.q.out b/ql/src/test/results/clientpositive/input25.q.out index d0a97fa..26722a1 100644 --- a/ql/src/test/results/clientpositive/input25.q.out +++ b/ql/src/test/results/clientpositive/input25.q.out @@ -36,110 +36,66 @@ select * from ( POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-3 - Stage-3 is a root stage - Stage-0 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: x + alias: null-subquery1:subq-subquery1:a:x Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: a (type: int), b (type: int) - outputColumnNames: _col0, _col1 + expressions: a (type: int), b (type: int), '2009-01-01' (type: string) + outputColumnNames: a, b, d Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int), VALUE._col1 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), '2009-01-01' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Union - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Union + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: a (type: int), b (type: int), d (type: string) + outputColumnNames: a, b, d + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - Union - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: x + alias: null-subquery2:subq-subquery2:b:x Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: a (type: int), b (type: int) - outputColumnNames: _col0, _col1 + expressions: a (type: int), b (type: int), '2009-02-02' (type: string) + outputColumnNames: a, b, d Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: a (type: int), b (type: int), d (type: string) + outputColumnNames: a, b, d Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int), VALUE._col1 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), '2009-02-02' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Union + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: a (type: int), b (type: int), d (type: string) + outputColumnNames: a, b, d + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator - limit: -1 + limit: 10 Processor Tree: ListSink diff --git a/ql/src/test/results/clientpositive/input26.q.out b/ql/src/test/results/clientpositive/input26.q.out index b917b86..8e58a43 100644 --- a/ql/src/test/results/clientpositive/input26.q.out +++ b/ql/src/test/results/clientpositive/input26.q.out @@ -14,8 +14,7 @@ select * from ( POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-3 - Stage-3 is a root stage + Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 STAGE PLANS: @@ -23,35 +22,31 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: null-subquery1:subq-subquery1:pa:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string), '2008-04-08' (type: string), '11' (type: string) + outputColumnNames: key, value, ds, hr Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), '11' (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -60,8 +55,8 @@ STAGE PLANS: Union Statistics: Num rows: 6 Data size: 50 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) + outputColumnNames: key, value, ds, hr Statistics: Num rows: 6 Data size: 50 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -71,62 +66,39 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - Union - Statistics: Num rows: 6 Data size: 50 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 50 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 50 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: a + alias: null-subquery2:subq-subquery2:pb:b Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((ds = '2008-04-08') and (hr = '14')) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string), '2008-04-08' (type: string), '14' (type: string) + outputColumnNames: key, value, ds, hr Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Limit Number of rows: 5 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) + outputColumnNames: key, value, ds, hr Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Limit - Number of rows: 5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), '14' (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Union + Statistics: Num rows: 6 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 6 Data size: 50 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 50 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator - limit: -1 + limit: 5 Processor Tree: ListSink diff --git a/ql/src/test/results/clientpositive/input2_limit.q.out b/ql/src/test/results/clientpositive/input2_limit.q.out index 76d1102..24d589d 100644 --- a/ql/src/test/results/clientpositive/input2_limit.q.out +++ b/ql/src/test/results/clientpositive/input2_limit.q.out @@ -20,7 +20,7 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 diff --git a/ql/src/test/results/clientpositive/input30.q.out b/ql/src/test/results/clientpositive/input30.q.out index c4848a1..5cc2385 100644 --- a/ql/src/test/results/clientpositive/input30.q.out +++ b/ql/src/test/results/clientpositive/input30.q.out @@ -34,11 +34,12 @@ STAGE PLANS: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((hash(rand(460476415)) & 2147483647) % 32) = 0) (type: boolean) - Statistics: Num rows: 250 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -50,10 +51,10 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: UDFToInteger(_col0) (type: int) + expressions: UDFToInteger($f0) (type: int) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -97,4 +98,4 @@ POSTHOOK: query: select * from tst_dest30 POSTHOOK: type: QUERY POSTHOOK: Input: default@tst_dest30 #### A masked pattern was here #### -18 +500 diff --git a/ql/src/test/results/clientpositive/input31.q.out b/ql/src/test/results/clientpositive/input31.q.out index 264ebe5..68ec2ca 100644 --- a/ql/src/test/results/clientpositive/input31.q.out +++ b/ql/src/test/results/clientpositive/input31.q.out @@ -33,34 +33,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcbucket - Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean) - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 1000 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count($f0) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: UDFToInteger(_col0) (type: int) + expressions: UDFToInteger($f0) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -99,4 +98,4 @@ POSTHOOK: query: select * from tst_dest31 POSTHOOK: type: QUERY POSTHOOK: Input: default@tst_dest31 #### A masked pattern was here #### -493 +1000 diff --git a/ql/src/test/results/clientpositive/input32.q.out b/ql/src/test/results/clientpositive/input32.q.out index c8fdfd4..4005e0c 100644 --- a/ql/src/test/results/clientpositive/input32.q.out +++ b/ql/src/test/results/clientpositive/input32.q.out @@ -35,9 +35,11 @@ STAGE PLANS: alias: srcbucket Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 1000 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -49,10 +51,10 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: UDFToInteger(_col0) (type: int) + expressions: UDFToInteger($f0) (type: int) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator diff --git a/ql/src/test/results/clientpositive/input38.q.out b/ql/src/test/results/clientpositive/input38.q.out index 0c4e81d..4c8e34c 100644 --- a/ql/src/test/results/clientpositive/input38.q.out +++ b/ql/src/test/results/clientpositive/input38.q.out @@ -50,14 +50,18 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 Stage: Stage-7 Conditional Operator diff --git a/ql/src/test/results/clientpositive/input39.q.out b/ql/src/test/results/clientpositive/input39.q.out index 66d8573..f1876cf 100644 --- a/ql/src/test/results/clientpositive/input39.q.out +++ b/ql/src/test/results/clientpositive/input39.q.out @@ -101,17 +101,19 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -127,13 +129,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/input4.q.java1.7.out b/ql/src/test/results/clientpositive/input4.q.java1.7.out index dccf625..50bc8c6 100644 --- a/ql/src/test/results/clientpositive/input4.q.java1.7.out +++ b/ql/src/test/results/clientpositive/input4.q.java1.7.out @@ -48,7 +48,7 @@ PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN FORMATTED SELECT Input4Alias.VALUE, Input4Alias.KEY FROM INPUT4 AS Input4Alias POSTHOOK: type: QUERY -{"STAGE PLANS":{"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"TableScan":{"alias:":"input4alias","children":{"Select Operator":{"expressions:":"value (type: string), key (type: string)","outputColumnNames:":["_col0","_col1"],"children":{"ListSink":{}},"Statistics:":"Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE"}}}}},"STAGE DEPENDENCIES":{"Stage-0":{"ROOT STAGE":"TRUE"}}} +{"STAGE PLANS":{"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"TableScan":{"alias:":"input4alias","children":{"Select Operator":{"expressions:":"value (type: string), key (type: string)","outputColumnNames:":["value","key"],"children":{"ListSink":{}},"Statistics:":"Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE"}}}}},"STAGE DEPENDENCIES":{"Stage-0":{"ROOT STAGE":"TRUE"}}} PREHOOK: query: SELECT Input4Alias.VALUE, Input4Alias.KEY FROM INPUT4 AS Input4Alias PREHOOK: type: QUERY PREHOOK: Input: default@input4 diff --git a/ql/src/test/results/clientpositive/input42.q.out b/ql/src/test/results/clientpositive/input42.q.out index 2974159..72f6ca3 100644 --- a/ql/src/test/results/clientpositive/input42.q.out +++ b/ql/src/test/results/clientpositive/input42.q.out @@ -135,7 +135,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1293,7 +1293,7 @@ STAGE PLANS: Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1819,32 +1819,128 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart + Partition + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 11 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Partition + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 12 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart Processor Tree: TableScan alias: a - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (rand(100) < 0.1) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Filter Operator + isSamplingPred: false + predicate: ((ds = '2008-04-08') and (rand(100) < 0.1)) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - ListSink + Select Operator + expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + ListSink PREHOOK: query: select * from srcpart a where a.ds='2008-04-08' and rand(100) < 0.1 PREHOOK: type: QUERY PREHOOK: Input: default@srcpart PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### POSTHOOK: query: select * from srcpart a where a.ds='2008-04-08' and rand(100) < 0.1 POSTHOOK: type: QUERY POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 113 val_113 2008-04-08 11 118 val_118 2008-04-08 11 diff --git a/ql/src/test/results/clientpositive/input6.q.out b/ql/src/test/results/clientpositive/input6.q.out index 5ed2767..2e824a4 100644 --- a/ql/src/test/results/clientpositive/input6.q.out +++ b/ql/src/test/results/clientpositive/input6.q.out @@ -36,7 +36,7 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: null (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/input_limit.q.out b/ql/src/test/results/clientpositive/input_limit.q.out index d1d62ec..feae4b8 100644 --- a/ql/src/test/results/clientpositive/input_limit.q.out +++ b/ql/src/test/results/clientpositive/input_limit.q.out @@ -17,7 +17,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 diff --git a/ql/src/test/results/clientpositive/input_part0.q.out b/ql/src/test/results/clientpositive/input_part0.q.out index f1853aa..5a026e2 100644 --- a/ql/src/test/results/clientpositive/input_part0.q.out +++ b/ql/src/test/results/clientpositive/input_part0.q.out @@ -17,7 +17,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/input_part10.q.out b/ql/src/test/results/clientpositive/input_part10.q.out index e4058b0..05aee39 100644 --- a/ql/src/test/results/clientpositive/input_part10.q.out +++ b/ql/src/test/results/clientpositive/input_part10.q.out @@ -34,8 +34,13 @@ SELECT 1, 2 FROM src LIMIT 1 POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 @@ -45,29 +50,29 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 1 (type: int), 2 (type: int) + outputColumnNames: _o__c0, _o__c1 Statistics: Num rows: 500 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Select Operator - expressions: 1 (type: int), 2 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.part_special + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.part_special + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -85,6 +90,36 @@ STAGE PLANS: Stage: Stage-2 Stats-Aggr Operator + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.part_special + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.part_special + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: INSERT OVERWRITE TABLE part_special PARTITION(ds='2008 04 08', ts = '10:11:12=455') SELECT 1, 2 FROM src LIMIT 1 PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/input_part3.q.out b/ql/src/test/results/clientpositive/input_part3.q.out index 3514bb7..c0d1228 100644 --- a/ql/src/test/results/clientpositive/input_part3.q.out +++ b/ql/src/test/results/clientpositive/input_part3.q.out @@ -17,7 +17,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), '11' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/input_part4.q.out b/ql/src/test/results/clientpositive/input_part4.q.out index 1c00c2d..512befa 100644 --- a/ql/src/test/results/clientpositive/input_part4.q.out +++ b/ql/src/test/results/clientpositive/input_part4.q.out @@ -20,7 +20,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), '15' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/input_part5.q.out b/ql/src/test/results/clientpositive/input_part5.q.out index f2d7335..0d0a6b6 100644 --- a/ql/src/test/results/clientpositive/input_part5.q.out +++ b/ql/src/test/results/clientpositive/input_part5.q.out @@ -36,7 +36,7 @@ STAGE PLANS: Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/input_part6.q.out b/ql/src/test/results/clientpositive/input_part6.q.out index fa51cdf..a6b5b16 100644 --- a/ql/src/test/results/clientpositive/input_part6.q.out +++ b/ql/src/test/results/clientpositive/input_part6.q.out @@ -20,7 +20,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '1996' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 diff --git a/ql/src/test/results/clientpositive/input_part8.q.out b/ql/src/test/results/clientpositive/input_part8.q.out index 0fef273..ad58e34 100644 --- a/ql/src/test/results/clientpositive/input_part8.q.out +++ b/ql/src/test/results/clientpositive/input_part8.q.out @@ -17,7 +17,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 diff --git a/ql/src/test/results/clientpositive/input_part9.q.out b/ql/src/test/results/clientpositive/input_part9.q.out index d95fee4..24e8470 100644 --- a/ql/src/test/results/clientpositive/input_part9.q.out +++ b/ql/src/test/results/clientpositive/input_part9.q.out @@ -144,7 +144,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/insert0.q.out b/ql/src/test/results/clientpositive/insert0.q.out index e83bae1..57e40d8 100644 --- a/ql/src/test/results/clientpositive/insert0.q.out +++ b/ql/src/test/results/clientpositive/insert0.q.out @@ -101,7 +101,7 @@ POSTHOOK: query: describe extended ctas_table POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@ctas_table key string -foo bigint +$f1 bigint #### A masked pattern was here #### PREHOOK: query: select * from ctas_table order by key diff --git a/ql/src/test/results/clientpositive/insert1.q.out b/ql/src/test/results/clientpositive/insert1.q.out index 49dd2d5..06c6f7c 100644 --- a/ql/src/test/results/clientpositive/insert1.q.out +++ b/ql/src/test/results/clientpositive/insert1.q.out @@ -54,7 +54,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: -1 (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false @@ -143,7 +143,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: -1 (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false @@ -248,7 +248,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: -1 (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false @@ -337,7 +337,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: -1 (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/insert1_overwrite_partitions.q.out b/ql/src/test/results/clientpositive/insert1_overwrite_partitions.q.out index 900babe..709671d 100644 --- a/ql/src/test/results/clientpositive/insert1_overwrite_partitions.q.out +++ b/ql/src/test/results/clientpositive/insert1_overwrite_partitions.q.out @@ -52,16 +52,16 @@ STAGE PLANS: Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: one (type: string), two (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: one, two Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: one (type: string), two (type: string) sort order: -- Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: one, two Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 @@ -184,16 +184,16 @@ STAGE PLANS: Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: one (type: string), two (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: one, two Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: one (type: string), two (type: string) sort order: -- Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: one, two Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 diff --git a/ql/src/test/results/clientpositive/insert2_overwrite_partitions.q.out b/ql/src/test/results/clientpositive/insert2_overwrite_partitions.q.out index 25c438f..fa0a138 100644 --- a/ql/src/test/results/clientpositive/insert2_overwrite_partitions.q.out +++ b/ql/src/test/results/clientpositive/insert2_overwrite_partitions.q.out @@ -63,16 +63,16 @@ STAGE PLANS: Statistics: Num rows: 30 Data size: 6028 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: one (type: string), two (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: one, two Statistics: Num rows: 30 Data size: 6028 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: one (type: string), two (type: string) sort order: -- Statistics: Num rows: 30 Data size: 6028 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: one, two Statistics: Num rows: 30 Data size: 6028 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 @@ -150,16 +150,16 @@ STAGE PLANS: Statistics: Num rows: 30 Data size: 6028 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: one (type: string), two (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: one, two Statistics: Num rows: 30 Data size: 6028 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: one (type: string), two (type: string) sort order: -- Statistics: Num rows: 30 Data size: 6028 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: one, two Statistics: Num rows: 30 Data size: 6028 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 diff --git a/ql/src/test/results/clientpositive/insert_into1.q.out b/ql/src/test/results/clientpositive/insert_into1.q.out index 2b5cbca..2eba82d 100644 --- a/ql/src/test/results/clientpositive/insert_into1.q.out +++ b/ql/src/test/results/clientpositive/insert_into1.q.out @@ -32,23 +32,23 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -139,23 +139,23 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -246,23 +246,23 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/insert_into2.q.out b/ql/src/test/results/clientpositive/insert_into2.q.out index cc7e135..1b3380e 100644 --- a/ql/src/test/results/clientpositive/insert_into2.q.out +++ b/ql/src/test/results/clientpositive/insert_into2.q.out @@ -32,23 +32,23 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -180,23 +180,23 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -297,23 +297,23 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 50 Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/insert_into4.q.out b/ql/src/test/results/clientpositive/insert_into4.q.out index 192e60e..2ffb4bf 100644 --- a/ql/src/test/results/clientpositive/insert_into4.q.out +++ b/ql/src/test/results/clientpositive/insert_into4.q.out @@ -28,8 +28,13 @@ POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 @@ -40,35 +45,32 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: UDFToInteger(key) (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.insert_into4a + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert_into4a + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -83,6 +85,36 @@ STAGE PLANS: Stage: Stage-2 Stats-Aggr Operator + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert_into4a + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert_into4a + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10 PREHOOK: type: QUERY PREHOOK: Input: default@src @@ -112,8 +144,13 @@ POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 @@ -124,35 +161,32 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: UDFToInteger(key) (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.insert_into4a + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert_into4a + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -167,6 +201,36 @@ STAGE PLANS: Stage: Stage-2 Stats-Aggr Operator + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert_into4a + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert_into4a + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10 PREHOOK: type: QUERY PREHOOK: Input: default@src @@ -217,7 +281,7 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/insert_into5.q.out b/ql/src/test/results/clientpositive/insert_into5.q.out index ea88b96..38685b5 100644 --- a/ql/src/test/results/clientpositive/insert_into5.q.out +++ b/ql/src/test/results/clientpositive/insert_into5.q.out @@ -28,8 +28,13 @@ POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into5a SELECT 1, 'one' FROM sr POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 @@ -39,29 +44,29 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 1 (type: int), 'one' (type: string) + outputColumnNames: _o__c0, _o__c1 Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: + File Output Operator + compressed: false Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Select Operator - expressions: 1 (type: int), 'one' (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.insert_into5a + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert_into5a + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -76,6 +81,36 @@ STAGE PLANS: Stage: Stage-2 Stats-Aggr Operator + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert_into5a + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert_into5a + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: INSERT INTO TABLE insert_into5a SELECT 1, 'one' FROM src LIMIT 10 PREHOOK: type: QUERY PREHOOK: Input: default@src @@ -122,7 +157,7 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -233,7 +268,7 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -348,7 +383,7 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/insert_into6.q.out b/ql/src/test/results/clientpositive/insert_into6.q.out index 388b200..e3b7091 100644 --- a/ql/src/test/results/clientpositive/insert_into6.q.out +++ b/ql/src/test/results/clientpositive/insert_into6.q.out @@ -30,8 +30,13 @@ POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into6a PARTITION (ds='1') POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 @@ -42,35 +47,32 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 150 Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: UDFToInteger(key) (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 150 - Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.insert_into6a + File Output Operator + compressed: false + Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert_into6a + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -87,6 +89,36 @@ STAGE PLANS: Stage: Stage-2 Stats-Aggr Operator + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert_into6a + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert_into6a + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: INSERT INTO TABLE insert_into6a PARTITION (ds='1') SELECT * FROM src LIMIT 150 PREHOOK: type: QUERY PREHOOK: Input: default@src @@ -149,7 +181,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 250 Data size: 2680 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/interval_arithmetic.q.out b/ql/src/test/results/clientpositive/interval_arithmetic.q.out index b6c3fdf..4fb1e9f 100644 --- a/ql/src/test/results/clientpositive/interval_arithmetic.q.out +++ b/ql/src/test/results/clientpositive/interval_arithmetic.q.out @@ -57,7 +57,7 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dateval (type: date), (dateval - 2-2) (type: date), (dateval - -2-2) (type: date), (dateval + 2-2) (type: date), (dateval + -2-2) (type: date), (-2-2 + dateval) (type: date), (2-2 + dateval) (type: date) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: dateval, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6 Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 2 @@ -135,7 +135,7 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dateval (type: date), (dateval - 1999-06-07) (type: interval_day_time), (1999-06-07 - dateval) (type: interval_day_time), (dateval - dateval) (type: interval_day_time) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: dateval, _o__c1, _o__c2, _o__c3 Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 2 @@ -213,7 +213,7 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: tsval (type: timestamp), (tsval - 2-2) (type: timestamp), (tsval - -2-2) (type: timestamp), (tsval + 2-2) (type: timestamp), (tsval + -2-2) (type: timestamp), (-2-2 + tsval) (type: timestamp), (2-2 + tsval) (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: tsval, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6 Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 2 @@ -287,7 +287,7 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 5-5 (type: interval_year_month), -1-1 (type: interval_year_month) - outputColumnNames: _col0, _col1 + outputColumnNames: _o__c0, _o__c1 Statistics: Num rows: 12288 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Limit Number of rows: 2 @@ -351,7 +351,7 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dateval (type: date), (dateval - 99 11:22:33.123456789) (type: timestamp), (dateval - -99 11:22:33.123456789) (type: timestamp), (dateval + 99 11:22:33.123456789) (type: timestamp), (dateval + -99 11:22:33.123456789) (type: timestamp), (-99 11:22:33.123456789 + dateval) (type: timestamp), (99 11:22:33.123456789 + dateval) (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: dateval, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6 Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 2 @@ -431,7 +431,7 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dateval (type: date), tsval (type: timestamp), (dateval - tsval) (type: interval_day_time), (tsval - dateval) (type: interval_day_time), (tsval - tsval) (type: interval_day_time) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: dateval, tsval, _o__c2, _o__c3, _o__c4 Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 2 @@ -511,7 +511,7 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: tsval (type: timestamp), (tsval - 99 11:22:33.123456789) (type: timestamp), (tsval - -99 11:22:33.123456789) (type: timestamp), (tsval + 99 11:22:33.123456789) (type: timestamp), (tsval + -99 11:22:33.123456789) (type: timestamp), (-99 11:22:33.123456789 + tsval) (type: timestamp), (99 11:22:33.123456789 + tsval) (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: tsval, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6 Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 2 @@ -585,7 +585,7 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 109 20:30:40.246913578 (type: interval_day_time), 89 02:14:26.000000000 (type: interval_day_time) - outputColumnNames: _col0, _col1 + outputColumnNames: _o__c0, _o__c1 Statistics: Num rows: 12288 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Limit Number of rows: 2 diff --git a/ql/src/test/results/clientpositive/ivyDownload.q.out b/ql/src/test/results/clientpositive/ivyDownload.q.out index 23cc124..7c06653 100644 --- a/ql/src/test/results/clientpositive/ivyDownload.q.out +++ b/ql/src/test/results/clientpositive/ivyDownload.q.out @@ -37,7 +37,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 3 (type: int), 6 (type: int), 10 (type: int), 3.3000000000000003 (type: double), 6.6 (type: double), 11.0 (type: double), 10.4 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6 Statistics: Num rows: 500 Data size: 22000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 diff --git a/ql/src/test/results/clientpositive/join0.q.java1.7.out b/ql/src/test/results/clientpositive/join0.q.java1.7.out index fa55ffb..eef3a29 100644 --- a/ql/src/test/results/clientpositive/join0.q.java1.7.out +++ b/ql/src/test/results/clientpositive/join0.q.java1.7.out @@ -67,12 +67,16 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -118,7 +122,7 @@ SELECT src1.key as k1, src1.value as v1, (SELECT * FROM src WHERE src.key < 10) src2 SORT BY k1, v1, k2, v2 POSTHOOK: type: QUERY -{"STAGE PLANS":{"Stage-2":{"Map Reduce":{"Reduce Operator Tree:":{"Select Operator":{"expressions:":"KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)","outputColumnNames:":["_col0","_col1","_col2","_col3"],"children":{"File Output Operator":{"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","compressed:":"false","table:":{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"}}},"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE"}},"Map Operator Tree:":[{"TableScan":{"children":{"Reduce Output Operator":{"sort order:":"++++","Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","key expressions:":"_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)"}}}}]}},"Stage-1":{"Map Reduce":{"Reduce Operator Tree:":{"Join Operator":{"keys:":{},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"children":{"File Output Operator":{"compressed:":"false","table:":{"serde:":"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe","input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat"}}},"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","condition map:":[{"":"Inner Join 0 to 1"}]}},"Map Operator Tree:":[{"TableScan":{"alias:":"src","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","outputColumnNames:":["_col0","_col1"],"children":{"Reduce Output Operator":{"sort order:":"","value expressions:":"_col0 (type: string), _col1 (type: string)","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE"}},{"TableScan":{"alias:":"src","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","outputColumnNames:":["_col0","_col1"],"children":{"Reduce Output Operator":{"sort order:":"","value expressions:":"_col0 (type: string), _col1 (type: string)","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE"}}]}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{}}}}},"STAGE DEPENDENCIES":{"Stage-2":{"DEPENDENT STAGES":"Stage-1"},"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-0":{"DEPENDENT STAGES":"Stage-2"}}} +{"STAGE PLANS":{"Stage-2":{"Map Reduce":{"Reduce Operator Tree:":{"Select Operator":{"expressions:":"KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)","outputColumnNames:":["_col0","_col1","_col2","_col3"],"children":{"File Output Operator":{"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","compressed:":"false","table:":{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"}}},"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE"}},"Map Operator Tree:":[{"TableScan":{"children":{"Reduce Output Operator":{"sort order:":"++++","Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","key expressions:":"_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)"}}}}]}},"Stage-1":{"Map Reduce":{"Reduce Operator Tree:":{"Join Operator":{"keys:":{},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"children":{"Select Operator":{"expressions:":"_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)","outputColumnNames:":["_col0","_col1","_col2","_col3"],"children":{"File Output Operator":{"compressed:":"false","table:":{"serde:":"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe","input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat"}}},"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","condition map:":[{"":"Inner Join 0 to 1"}]}},"Map Operator Tree:":[{"TableScan":{"alias:":"src","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","outputColumnNames:":["_col0","_col1"],"children":{"Reduce Output Operator":{"sort order:":"","value expressions:":"_col0 (type: string), _col1 (type: string)","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE"}},{"TableScan":{"alias:":"src","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","outputColumnNames:":["_col0","_col1"],"children":{"Reduce Output Operator":{"sort order:":"","value expressions:":"_col0 (type: string), _col1 (type: string)","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE"}}]}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{}}}}},"STAGE DEPENDENCIES":{"Stage-2":{"DEPENDENT STAGES":"Stage-1"},"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-0":{"DEPENDENT STAGES":"Stage-2"}}} Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT src1.key as k1, src1.value as v1, src2.key as k2, src2.value as v2 FROM diff --git a/ql/src/test/results/clientpositive/join10.q.out b/ql/src/test/results/clientpositive/join10.q.out index 6309059..e1579ad 100644 --- a/ql/src/test/results/clientpositive/join10.q.out +++ b/ql/src/test/results/clientpositive/join10.q.out @@ -25,52 +25,56 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: y:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src + alias: x:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/join11.q.out b/ql/src/test/results/clientpositive/join11.q.out index 46875b2..eb67b7c 100644 --- a/ql/src/test/results/clientpositive/join11.q.out +++ b/ql/src/test/results/clientpositive/join11.q.out @@ -27,48 +27,48 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: src2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + expressions: key0 (type: string), value (type: string) + outputColumnNames: c1, c4 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/join12.q.out b/ql/src/test/results/clientpositive/join12.q.out index bdb5496..b99ade8 100644 --- a/ql/src/test/results/clientpositive/join12.q.out +++ b/ql/src/test/results/clientpositive/join12.q.out @@ -25,102 +25,109 @@ JOIN ON src1.c1 = src3.c5 AND src3.c5 < 80 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-1 + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(key) < 100.0) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src + alias: src2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(key) < 100.0) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean) + Statistics: Num rows: 20 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 20 Data size: 213 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-1 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: src + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 20 Data size: 213 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + TableScan + alias: src3:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 80.0) and (UDFToDouble(key) < 100.0)) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) < 80.0) and (UDFToDouble(key) < 100.0)) (type: boolean) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col3 - Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: c1, c4 + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/join13.q.out b/ql/src/test/results/clientpositive/join13.q.out index 3b921b9..7f29aa3 100644 --- a/ql/src/test/results/clientpositive/join13.q.out +++ b/ql/src/test/results/clientpositive/join13.q.out @@ -34,48 +34,48 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: src2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(_col2) + UDFToDouble(_col0)) is not null (type: boolean) - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key0) + UDFToDouble(key)) < 200.0) (type: boolean) + Statistics: Num rows: 60 Data size: 639 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -88,42 +88,42 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) + key expressions: (UDFToDouble(key0) + UDFToDouble(key)) (type: double) sort order: + - Map-reduce partition columns: (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string) + Map-reduce partition columns: (UDFToDouble(key0) + UDFToDouble(key)) (type: double) + Statistics: Num rows: 60 Data size: 639 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string), key0 (type: string) TableScan - alias: src + alias: src3:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) < 200.0) and UDFToDouble(key) is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(key) < 200.0) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) + key expressions: UDFToDouble(key) (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: UDFToDouble(key) (type: double) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE + 0 (UDFToDouble(key0) + UDFToDouble(key)) (type: double) + 1 UDFToDouble(key) (type: double) + outputColumnNames: value, key0 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE + expressions: key0 (type: string), value (type: string) + outputColumnNames: c1, c4 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/join14.q.out b/ql/src/test/results/clientpositive/join14.q.out index 8b1d399..2563edf 100644 --- a/ql/src/test/results/clientpositive/join14.q.out +++ b/ql/src/test/results/clientpositive/join14.q.out @@ -37,14 +37,14 @@ STAGE PLANS: Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -53,24 +53,24 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col3) (type: int), _col1 (type: string) + expressions: UDFToInteger(key0) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/join16.q.out b/ql/src/test/results/clientpositive/join16.q.out index a5e9f76..da10bf5 100644 --- a/ql/src/test/results/clientpositive/join16.q.out +++ b/ql/src/test/results/clientpositive/join16.q.out @@ -11,51 +11,51 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: subq:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) > 20.0)) and (UDFToDouble(value) < 200.0)) and key is not null) and value is not null) (type: boolean) - Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + predicate: (((((UDFToDouble(key) > 10.0) and value is not null) and key is not null) and (UDFToDouble(key) > 20.0)) and (UDFToDouble(value) < 200.0)) (type: boolean) + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE TableScan - alias: a + alias: tab Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(value) < 200.0) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) > 20.0)) and key is not null) and value is not null) (type: boolean) - Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + predicate: ((((value is not null and key is not null) and (UDFToDouble(value) < 200.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) > 20.0)) (type: boolean) + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 5 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 5 Data size: 58 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string), value (type: string) + 1 key (type: string), value (type: string) + outputColumnNames: key, value0 + Statistics: Num rows: 4 Data size: 46 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 58 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value0 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 4 Data size: 46 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 58 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 46 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/join17.q.out b/ql/src/test/results/clientpositive/join17.q.out index 26aabcf..1561a6b 100644 --- a/ql/src/test/results/clientpositive/join17.q.out +++ b/ql/src/test/results/clientpositive/join17.q.out @@ -75,18 +75,18 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false TableScan - alias: src1 + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator @@ -95,15 +95,15 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -153,19 +153,19 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_0:src1, $hdt$_1:src1] + /src [src1, src2] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string), UDFToInteger(key0) (type: int), value0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -232,9 +232,9 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.key1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.key2 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.key2 EXPRESSION [(src)src2.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest1.value1 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.value2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.value2 SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git a/ql/src/test/results/clientpositive/join18.q.out b/ql/src/test/results/clientpositive/join18.q.out index c3ab306..5b0bfe5 100644 --- a/ql/src/test/results/clientpositive/join18.q.out +++ b/ql/src/test/results/clientpositive/join18.q.out @@ -39,15 +39,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: a:src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -62,7 +62,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -76,48 +76,52 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, key0, $f10 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: bigint), key0 (type: string), $f10 (type: bigint) + outputColumnNames: key, $f1, key0, $f10 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: src2 + alias: b:src2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT value) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -131,7 +135,7 @@ STAGE PLANS: aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/join18_multi_distinct.q.out b/ql/src/test/results/clientpositive/join18_multi_distinct.q.out index a83102c..0c04458 100644 --- a/ql/src/test/results/clientpositive/join18_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/join18_multi_distinct.q.out @@ -41,15 +41,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: a:src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -64,7 +64,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -78,48 +78,52 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint), _col2 (type: bigint) + value expressions: $f1 (type: bigint), $f2 (type: bigint) Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, key0, $f10, $f2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: bigint), key0 (type: string), $f10 (type: bigint), $f2 (type: bigint) + outputColumnNames: key, $f1, key0, $f10, $f2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: src2 + alias: b:src2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), count(DISTINCT _col0) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT value), count(DISTINCT key) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -133,7 +137,7 @@ STAGE PLANS: aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, $f1, $f2 Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/join2.q.out b/ql/src/test/results/clientpositive/join2.q.out index d59aed2..e81cebd 100644 --- a/ql/src/test/results/clientpositive/join2.q.out +++ b/ql/src/test/results/clientpositive/join2.q.out @@ -19,13 +19,13 @@ FROM src src1 JOIN src src2 ON (src1.key = src2.key) JOIN src src3 ON (src1.key INSERT OVERWRITE TABLE dest_j2 SELECT src1.key, src3.value POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 + Stage-3 is a root stage + Stage-1 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan @@ -36,89 +36,86 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src1 + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - Reduce Output Operator - key expressions: (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - sort order: + - Map-reduce partition columns: (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - TableScan - alias: src1 + alias: src3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: UDFToDouble(key) is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) + key expressions: UDFToDouble(key) (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Map-reduce partition columns: UDFToDouble(key) (type: double) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) + TableScan + Reduce Output Operator + key expressions: (UDFToDouble(key) + UDFToDouble(key0)) (type: double) + sort order: + + Map-reduce partition columns: (UDFToDouble(key) + UDFToDouble(key0)) (type: double) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + 0 UDFToDouble(key) (type: double) + 1 (UDFToDouble(key) + UDFToDouble(key0)) (type: double) + outputColumnNames: value, key0 + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col3 (type: string) + expressions: UDFToInteger(key0) (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -135,7 +132,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j2 - Stage: Stage-3 + Stage: Stage-2 Stats-Aggr Operator PREHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key) JOIN src src3 ON (src1.key + src2.key = src3.key) @@ -149,7 +146,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest_j2 POSTHOOK: Lineage: dest_j2.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j2.value SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j2.value SIMPLE [(src)src3.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest_j2.* FROM dest_j2 PREHOOK: type: QUERY PREHOOK: Input: default@dest_j2 diff --git a/ql/src/test/results/clientpositive/join22.q.out b/ql/src/test/results/clientpositive/join22.q.out index d7fc7ae..42ee660 100644 --- a/ql/src/test/results/clientpositive/join22.q.out +++ b/ql/src/test/results/clientpositive/join22.q.out @@ -6,101 +6,76 @@ SELECT src5.src1_value FROM (SELECT src3.*, src4.value as src4_value, src4.key a POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: src4 + alias: src5:src3:src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src4 + alias: src5:src3:src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) TableScan - alias: src4 + alias: src5:src4 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 + Inner Join 0 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: value + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + expressions: value (type: string) + outputColumnNames: src1_value + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/join28.q.out b/ql/src/test/results/clientpositive/join28.q.out index d748495..153db86 100644 --- a/ql/src/test/results/clientpositive/join28.q.out +++ b/ql/src/test/results/clientpositive/join28.q.out @@ -31,98 +31,90 @@ FROM JOIN srcpart z ON (subq.key1 = z.key and z.ds='2008-04-08' and z.hr=11) POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-7 is a root stage - Stage-5 depends on stages: Stage-7 + Stage-6 is a root stage + Stage-5 depends on stages: Stage-6 Stage-0 depends on stages: Stage-5 Stage-2 depends on stages: Stage-0 STAGE PLANS: - Stage: Stage-7 + Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:z + subq:x Fetch Operator limit: -1 - $hdt$_1:$hdt$_2:x + subq:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:z + subq:x TableScan - alias: z - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: subq:x + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - $hdt$_1:$hdt$_2:x + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + subq:y TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: subq:y + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) Stage: Stage-5 Map Reduce Map Operator Tree: TableScan - alias: y + alias: z Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 + Inner Join 1 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: key0, value1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col4 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col4 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest_j1 + expressions: key0 (type: string), value1 (type: string) + outputColumnNames: key1, value + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_j1 Local Work: Map Reduce Local Work @@ -163,7 +155,7 @@ POSTHOOK: Input: default@src1 POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Output: default@dest_j1 -POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)subq:x.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from dest_j1 PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/join29.q.out b/ql/src/test/results/clientpositive/join29.q.out index 15d0cbe..cb7dca48e 100644 --- a/ql/src/test/results/clientpositive/join29.q.out +++ b/ql/src/test/results/clientpositive/join29.q.out @@ -43,18 +43,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y + alias: subq2:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -69,7 +69,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -92,8 +92,8 @@ STAGE PLANS: TableScan HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 $f0 (type: string) + 1 $f0 (type: string) Stage: Stage-5 Map Reduce @@ -103,12 +103,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f1, $f00, $f10 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col1) (type: int) + expressions: $f00 (type: string), UDFToInteger($f10) (type: int), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -146,8 +146,8 @@ STAGE PLANS: TableScan HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 $f0 (type: string) + 1 $f0 (type: string) Stage: Stage-6 Map Reduce @@ -157,12 +157,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f1, $f00, $f10 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col1) (type: int) + expressions: $f00 (type: string), UDFToInteger($f10) (type: int), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -181,29 +181,29 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f1, $f00, $f10 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col1) (type: int) + expressions: $f00 (type: string), UDFToInteger($f10) (type: int), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -219,18 +219,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: subq1:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE @@ -245,7 +245,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -270,9 +270,9 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@dest_j1 -POSTHOOK: Lineage: dest_j1.cnt1 EXPRESSION [(src1)x.null, ] -POSTHOOK: Lineage: dest_j1.cnt2 EXPRESSION [(src)y.null, ] -POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j1.cnt1 EXPRESSION [(src1)subq1:x.null, ] +POSTHOOK: Lineage: dest_j1.cnt2 EXPRESSION [(src)subq2:y.null, ] +POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)subq1:x.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: select * from dest_j1 PREHOOK: type: QUERY PREHOOK: Input: default@dest_j1 diff --git a/ql/src/test/results/clientpositive/join3.q.out b/ql/src/test/results/clientpositive/join3.q.out index 7bb713f..a418ccb 100644 --- a/ql/src/test/results/clientpositive/join3.q.out +++ b/ql/src/test/results/clientpositive/join3.q.out @@ -35,57 +35,57 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src1 + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src1 + alias: src3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col3 + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: key, value1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col3 (type: string) + expressions: UDFToInteger(key) (type: int), value1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -121,7 +121,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.value SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.value SIMPLE [(src)src3.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git a/ql/src/test/results/clientpositive/join30.q.out b/ql/src/test/results/clientpositive/join30.q.out index c7b7918..2816f13 100644 --- a/ql/src/test/results/clientpositive/join30.q.out +++ b/ql/src/test/results/clientpositive/join30.q.out @@ -61,18 +61,22 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: diff --git a/ql/src/test/results/clientpositive/join31.q.out b/ql/src/test/results/clientpositive/join31.q.out index 21aa1de..9d7b267 100644 --- a/ql/src/test/results/clientpositive/join31.q.out +++ b/ql/src/test/results/clientpositive/join31.q.out @@ -46,17 +46,17 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: y + alias: subq2:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -69,7 +69,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -84,16 +84,16 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$INTNAME1 + $INTNAME1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$INTNAME1 + $INTNAME1 TableScan HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-6 Map Reduce @@ -103,17 +103,17 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE @@ -141,10 +141,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 68 Data size: 724 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + expressions: $f0 (type: string), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 68 Data size: 724 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -172,16 +172,16 @@ STAGE PLANS: Stage: Stage-10 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$INTNAME + $INTNAME Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$INTNAME + $INTNAME TableScan HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-7 Map Reduce @@ -191,17 +191,17 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE @@ -219,32 +219,32 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + expressions: key0 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE @@ -259,17 +259,17 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: subq1:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE @@ -282,7 +282,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -309,8 +309,8 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@dest_j1 -POSTHOOK: Lineage: dest_j1.cnt EXPRESSION [(src1)x.null, ] -POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j1.cnt EXPRESSION [(src1)subq1:x.null, ] +POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)subq1:x.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: select * from dest_j1 PREHOOK: type: QUERY PREHOOK: Input: default@dest_j1 diff --git a/ql/src/test/results/clientpositive/join32.q.out b/ql/src/test/results/clientpositive/join32.q.out index afb373d..0f7dc8a 100644 --- a/ql/src/test/results/clientpositive/join32.q.out +++ b/ql/src/test/results/clientpositive/join32.q.out @@ -100,95 +100,141 @@ TOK_QUERY STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-6 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-6 - Stage-3 depends on stages: Stage-0 + Stage-7 is a root stage + Stage-5 depends on stages: Stage-7 + Stage-0 depends on stages: Stage-5 + Stage-2 depends on stages: Stage-0 STAGE PLANS: - Stage: Stage-8 + Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:y + x Fetch Operator limit: -1 - $hdt$_2:x + z Fetch Operator limit: -1 + Partition Description: + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart Alias -> Map Local Operator Tree: - $hdt$_0:y + x TableScan - alias: y - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: x + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col3 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Position of Big Table: 0 - $hdt$_2:x + z TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: z + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (value is not null and key is not null) (type: boolean) - Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - Position of Big Table: 0 + 0 value (type: string) + 1 value0 (type: string) + Position of Big Table: 1 - Stage: Stage-6 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan - alias: z + alias: y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0, value0 Position of Big Table: 0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col3, _col6 - Position of Big Table: 0 + 0 value (type: string) + 1 value0 (type: string) + outputColumnNames: value, value0, key0 + Position of Big Table: 1 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col3 (type: string), _col0 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key0 (type: string), value (type: string), value0 (type: string) + outputColumnNames: key, value, value1 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -356,7 +402,7 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:z] + /src [y] Stage: Stage-0 Move Operator @@ -380,7 +426,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 - Stage: Stage-3 + Stage: Stage-2 Stats-Aggr Operator #### A masked pattern was here #### diff --git a/ql/src/test/results/clientpositive/join32_lessSize.q.out b/ql/src/test/results/clientpositive/join32_lessSize.q.out index 3c5f9e2..543b720 100644 --- a/ql/src/test/results/clientpositive/join32_lessSize.q.out +++ b/ql/src/test/results/clientpositive/join32_lessSize.q.out @@ -108,62 +108,62 @@ TOK_QUERY STAGE DEPENDENCIES: - Stage-9 is a root stage - Stage-7 depends on stages: Stage-9 - Stage-8 depends on stages: Stage-7 + Stage-8 is a root stage Stage-6 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-6 - Stage-3 depends on stages: Stage-0 + Stage-7 depends on stages: Stage-6 + Stage-5 depends on stages: Stage-7 + Stage-0 depends on stages: Stage-5 + Stage-2 depends on stages: Stage-0 STAGE PLANS: - Stage: Stage-9 + Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_2:x + x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_2:x + x TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (value is not null and key is not null) (type: boolean) + predicate: (key is not null and value is not null) (type: boolean) Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col1 (type: string) + 0 key (type: string) + 1 key (type: string) Position of Big Table: 0 - Stage: Stage-7 + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan - alias: z + alias: y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0, value0 Position of Big Table: 0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -175,8 +175,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col3 - columns.types string,string + columns value,key0,value0 + columns.types string,string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -190,7 +190,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: src1 + base file name: src input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: @@ -200,14 +200,14 @@ STAGE PLANS: columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.src1 + name default.src numFiles 1 - numRows 25 - rawDataSize 191 - serialization.ddl struct src1 { string key, string value} + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 216 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -220,26 +220,23 @@ STAGE PLANS: columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.src1 + name default.src numFiles 1 - numRows 25 - rawDataSize 191 - serialization.ddl struct src1 { string key, string value} + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 216 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src1 - name: default.src1 + name: default.src + name: default.src #### A masked pattern was here #### Partition - base file name: hr=11 + base file name: src1 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 properties: COLUMN_STATS_ACCURATE true bucket_count -1 @@ -247,67 +244,114 @@ STAGE PLANS: columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.srcpart + name default.src1 numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + totalSize 216 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: + COLUMN_STATS_ACCURATE true bucket_count -1 columns key,value columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart + name: default.src1 + name: default.src1 Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:z] + /src [y] - Stage: Stage-8 + Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:y + z Fetch Operator limit: -1 + Partition Description: + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart Alias -> Map Local Operator Tree: - $hdt$_0:y + z TableScan - alias: y + alias: z Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: key is not null (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: value (type: string) + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - Position of Big Table: 0 + 0 value (type: string) + 1 value0 (type: string) + Position of Big Table: 1 - Stage: Stage-6 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan @@ -316,14 +360,14 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col3, _col6 - Position of Big Table: 0 + 0 value (type: string) + 1 value0 (type: string) + outputColumnNames: value, value0, key0 + Position of Big Table: 1 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col3 (type: string), _col0 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key0 (type: string), value (type: string), value0 (type: string) + outputColumnNames: key, value, value1 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -362,8 +406,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col3 - columns.types string,string + columns value,key0,value0 + columns.types string,string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -371,16 +415,19 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col3 - columns.types string,string + columns value,key0,value0 + columns.types string,string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe #### A masked pattern was here #### Partition - base file name: src + base file name: hr=11 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 properties: COLUMN_STATS_ACCURATE true bucket_count -1 @@ -388,11 +435,13 @@ STAGE PLANS: columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.src + name default.srcpart numFiles 1 numRows 500 + partition_columns ds/hr + partition_columns.types string:string rawDataSize 5312 - serialization.ddl struct src { string key, string value} + serialization.ddl struct srcpart { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 @@ -402,24 +451,21 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - COLUMN_STATS_ACCURATE true bucket_count -1 columns key,value columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src + name: default.srcpart + name: default.srcpart Truncated Path -> Alias: #### A masked pattern was here #### @@ -445,7 +491,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 - Stage: Stage-3 + Stage: Stage-2 Stats-Aggr Operator #### A masked pattern was here #### @@ -653,83 +699,91 @@ TOK_QUERY STAGE DEPENDENCIES: - Stage-13 is a root stage - Stage-10 depends on stages: Stage-13 - Stage-12 depends on stages: Stage-10 - Stage-9 depends on stages: Stage-12 - Stage-11 depends on stages: Stage-9 - Stage-8 depends on stages: Stage-11 - Stage-0 depends on stages: Stage-8 - Stage-4 depends on stages: Stage-0 + Stage-14 is a root stage + Stage-10 depends on stages: Stage-14 + Stage-9 depends on stages: Stage-10 , consists of Stage-11, Stage-12, Stage-13, Stage-1 + Stage-11 has a backup stage: Stage-1 + Stage-6 depends on stages: Stage-11 + Stage-0 depends on stages: Stage-1, Stage-6, Stage-7, Stage-8 + Stage-2 depends on stages: Stage-0 + Stage-12 has a backup stage: Stage-1 + Stage-7 depends on stages: Stage-12 + Stage-13 has a backup stage: Stage-1 + Stage-8 depends on stages: Stage-13 + Stage-1 STAGE PLANS: - Stage: Stage-13 + Stage: Stage-14 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_2:x + x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_2:x + x TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (key is not null and value is not null) (type: boolean) + predicate: (value is not null and key is not null) (type: boolean) Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Position of Big Table: 1 + 0 value (type: string) + 1 value (type: string) + Position of Big Table: 0 Stage: Stage-10 Map Reduce Map Operator Tree: TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: w + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Position of Big Table: 1 - Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key + Position of Big Table: 0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col3 - columns.types string,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns key + columns.types string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Local Work: Map Reduce Local Work Path -> Alias: @@ -737,7 +791,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: src1 + base file name: src input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: @@ -747,14 +801,14 @@ STAGE PLANS: columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.src1 + name default.src numFiles 1 - numRows 25 - rawDataSize 191 - serialization.ddl struct src1 { string key, string value} + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 216 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -767,78 +821,631 @@ STAGE PLANS: columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.src1 + name default.src numFiles 1 - numRows 25 - rawDataSize 191 - serialization.ddl struct src1 { string key, string value} + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 216 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src1 - name: default.src1 - Truncated Path -> Alias: - /src1 [$hdt$_3:x] - - Stage: Stage-12 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_1:w - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_1:w + name: default.src + name: default.src +#### A masked pattern was here #### + Partition + base file name: src1 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src1 + name: default.src1 + Truncated Path -> Alias: + /src [w] + + Stage: Stage-9 + Conditional Operator + + Stage: Stage-11 + Map Reduce Local Work + Alias -> Map Local Tables: + $INTNAME + Fetch Operator + limit: -1 + z + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + $INTNAME + TableScan + GatherStats: false + HashTable Sink Operator + keys: + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + Position of Big Table: 0 + z + TableScan + alias: z + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + Position of Big Table: 0 + + Stage: Stage-6 + Map Reduce + Map Operator Tree: + TableScan + alias: y + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: value, key00, value1 + Position of Big Table: 0 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key00 (type: string), value1 (type: string), value (type: string) + outputColumnNames: key, value, value1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value,val2 + columns.comments + columns.types string:string:string +#### A masked pattern was here #### + name default.dest_j1 + numFiles 1 + numRows 85 + rawDataSize 1600 + serialization.ddl struct dest_j1 { string key, string value, string val2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 1685 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_j1 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + Local Work: + Map Reduce Local Work + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: -mr-10001 + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns key + columns.types string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns key + columns.types string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe +#### A masked pattern was here #### + Partition + base file name: src + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src +#### A masked pattern was here #### + Partition + base file name: src1 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src1 + name: default.src1 + Truncated Path -> Alias: + /src [y] + + Stage: Stage-0 + Move Operator + tables: + replace: true +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value,val2 + columns.comments + columns.types string:string:string +#### A masked pattern was here #### + name default.dest_j1 + numFiles 1 + numRows 85 + rawDataSize 1600 + serialization.ddl struct dest_j1 { string key, string value, string val2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 1685 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_j1 + + Stage: Stage-2 + Stats-Aggr Operator +#### A masked pattern was here #### + + Stage: Stage-12 + Map Reduce Local Work + Alias -> Map Local Tables: + y + Fetch Operator + limit: -1 + z + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + y + TableScan + alias: y + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + Position of Big Table: 1 + z + TableScan + alias: z + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + Position of Big Table: 1 + + Stage: Stage-7 + Map Reduce + Map Operator Tree: TableScan - alias: w + GatherStats: false + Map Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: value, key00, value1 + Position of Big Table: 1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key00 (type: string), value1 (type: string), value (type: string) + outputColumnNames: key, value, value1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value,val2 + columns.comments + columns.types string:string:string +#### A masked pattern was here #### + name default.dest_j1 + numFiles 1 + numRows 85 + rawDataSize 1600 + serialization.ddl struct dest_j1 { string key, string value, string val2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 1685 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_j1 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + Local Work: + Map Reduce Local Work + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: -mr-10001 + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns key + columns.types string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns key + columns.types string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe +#### A masked pattern was here #### + Partition + base file name: src + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src +#### A masked pattern was here #### + Partition + base file name: src1 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src1 + name: default.src1 + Truncated Path -> Alias: +#### A masked pattern was here #### + + Stage: Stage-13 + Map Reduce Local Work + Alias -> Map Local Tables: + $INTNAME + Fetch Operator + limit: -1 + y + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + $INTNAME + TableScan + GatherStats: false + HashTable Sink Operator + keys: + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + Position of Big Table: 2 + y + TableScan + alias: y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - Position of Big Table: 0 + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + Position of Big Table: 2 - Stage: Stage-9 + Stage: Stage-8 Map Reduce Map Operator Tree: TableScan + alias: z + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE GatherStats: false - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col3 - Position of Big Table: 0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col3 - columns.types string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: value, key00, value1 + Position of Big Table: 2 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key00 (type: string), value1 (type: string), value (type: string) + outputColumnNames: key, value, value1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value,val2 + columns.comments + columns.types string:string:string +#### A masked pattern was here #### + name default.dest_j1 + numFiles 1 + numRows 85 + rawDataSize 1600 + serialization.ddl struct dest_j1 { string key, string value, string val2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 1685 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_j1 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false Local Work: Map Reduce Local Work Path -> Alias: @@ -850,8 +1457,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col3 - columns.types string,string,string + columns key + columns.types string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -859,14 +1466,58 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col3 - columns.types string,string,string + columns key + columns.types string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe #### A masked pattern was here #### Partition - base file name: src + base file name: src + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src +#### A masked pattern was here #### + Partition + base file name: src1 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: @@ -876,14 +1527,14 @@ STAGE PLANS: columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.src + name default.src1 numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + totalSize 216 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -896,31 +1547,26 @@ STAGE PLANS: columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.src + name default.src1 numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + totalSize 216 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src + name: default.src1 + name: default.src1 Truncated Path -> Alias: -#### A masked pattern was here #### + /src1 [z] - Stage: Stage-11 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:w - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:w + Stage: Stage-1 + Map Reduce + Map Operator Tree: TableScan - alias: w + alias: y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator @@ -929,76 +1575,56 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Position of Big Table: 0 - - Stage: Stage-8 - Map Reduce - Map Operator Tree: + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: value (type: string) + auto parallelism: false TableScan GatherStats: false - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col3, _col6 - Position of Big Table: 0 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + tag: 1 + auto parallelism: false + TableScan + alias: z + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col3 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE true - bucket_count -1 - columns key,value,val2 - columns.comments - columns.types string:string:string -#### A masked pattern was here #### - name default.dest_j1 - numFiles 1 - numRows 85 - rawDataSize 1600 - serialization.ddl struct dest_j1 { string key, string value, string val2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 1685 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest_j1 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - Local Work: - Map Reduce Local Work + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + tag: 2 + value expressions: value (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10002 + base file name: -mr-10001 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col3 - columns.types string,string + columns key + columns.types string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -1006,8 +1632,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col3 - columns.types string,string + columns key + columns.types string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -1055,39 +1681,101 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src name: default.src - Truncated Path -> Alias: #### A masked pattern was here #### - - Stage: Stage-0 - Move Operator - tables: - replace: true + Partition + base file name: src1 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string #### A masked pattern was here #### - table: + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 - columns key,value,val2 - columns.comments - columns.types string:string:string + columns key,value + columns.comments 'default','default' + columns.types string:string #### A masked pattern was here #### - name default.dest_j1 + name default.src1 numFiles 1 - numRows 85 - rawDataSize 1600 - serialization.ddl struct dest_j1 { string key, string value, string val2} + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 1685 + totalSize 216 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest_j1 - - Stage: Stage-4 - Stats-Aggr Operator + name: default.src1 + name: default.src1 + Truncated Path -> Alias: + /src [y] + /src1 [z] +#### A masked pattern was here #### + Needs Tagging: true + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: value, key00, value1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key00 (type: string), value1 (type: string), value (type: string) + outputColumnNames: key, value, value1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value,val2 + columns.comments + columns.types string:string:string +#### A masked pattern was here #### + name default.dest_j1 + numFiles 1 + numRows 85 + rawDataSize 1600 + serialization.ddl struct dest_j1 { string key, string value, string val2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 1685 #### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_j1 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false PREHOOK: query: INSERT OVERWRITE TABLE dest_j1 SELECT x.key, z.value, y.value @@ -1108,8 +1796,8 @@ POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@dest_j1 POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)w.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j1.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j1.value SIMPLE [(src1)z.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from dest_j1 PREHOOK: type: QUERY PREHOOK: Input: default@dest_j1 @@ -1319,13 +2007,13 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:$hdt$_2:x + res:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:$hdt$_2:x + res:x TableScan - alias: x + alias: res:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator @@ -1334,19 +2022,19 @@ STAGE PLANS: Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Position of Big Table: 0 Stage: Stage-6 Map Reduce Map Operator Tree: TableScan - alias: y + alias: res:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator @@ -1355,38 +2043,34 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0, value Position of Big Table: 0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1 - columns.types string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns key0,value + columns.types string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Local Work: Map Reduce Local Work Path -> Alias: @@ -1481,12 +2165,12 @@ STAGE PLANS: name: default.src1 name: default.src1 Truncated Path -> Alias: - /src [$hdt$_1:$hdt$_1:y] + /src [res:y] Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:z + z Fetch Operator limit: -1 Partition Description: @@ -1536,7 +2220,7 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Alias -> Map Local Operator Tree: - $hdt$_0:z + z TableScan alias: z Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1547,12 +2231,12 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col1 (type: string) + 0 value (type: string) + 1 value (type: string) Position of Big Table: 1 Stage: Stage-5 @@ -1564,14 +2248,14 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3, _col4 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: value, key0, value0 Position of Big Table: 1 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key0 (type: string), value (type: string), value0 (type: string) + outputColumnNames: key, value, value1 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1610,7 +2294,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1 + columns key0,value columns.types string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -1619,7 +2303,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1 + columns key0,value columns.types string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -1719,8 +2403,8 @@ POSTHOOK: Input: default@src1 POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Output: default@dest_j2 -POSTHOOK: Lineage: dest_j2.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j2.val2 SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j2.key SIMPLE [(src1)res:x.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j2.val2 SIMPLE [(src1)res:x.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j2.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from dest_j2 PREHOOK: type: QUERY @@ -1931,30 +2615,30 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:y + res:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:y + res:y TableScan - alias: y + alias: res:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Position of Big Table: 1 Stage: Stage-7 Map Reduce Map Operator Tree: TableScan - alias: x + alias: res:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator @@ -1963,38 +2647,34 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0, value Position of Big Table: 1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1 - columns.types string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns key0,value + columns.types string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Local Work: Map Reduce Local Work Path -> Alias: @@ -2089,12 +2769,12 @@ STAGE PLANS: name: default.src1 name: default.src1 Truncated Path -> Alias: - /src1 [$hdt$_0:$hdt$_1:x] + /src1 [res:x] Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:z + z Fetch Operator limit: -1 Partition Description: @@ -2144,7 +2824,7 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Alias -> Map Local Operator Tree: - $hdt$_1:z + z TableScan alias: z Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -2155,12 +2835,12 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col1 (type: string) - 1 _col0 (type: string) + 0 value (type: string) + 1 value (type: string) Position of Big Table: 0 Stage: Stage-6 @@ -2172,14 +2852,14 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key0, value, value0 Position of Big Table: 0 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key0 (type: string), value0 (type: string), value (type: string) + outputColumnNames: key, value, value1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2223,7 +2903,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1 + columns key0,value columns.types string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -2232,7 +2912,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1 + columns key0,value columns.types string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -2337,8 +3017,8 @@ POSTHOOK: Input: default@src1 POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Output: default@dest_j2 -POSTHOOK: Lineage: dest_j2.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j2.val2 SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j2.key SIMPLE [(src1)res:x.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j2.val2 SIMPLE [(src1)res:x.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j2.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from dest_j2 PREHOOK: type: QUERY @@ -2469,68 +3149,64 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:$hdt$_2:x + res:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:$hdt$_2:x + res:x TableScan - alias: x + alias: res:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and value is not null) (type: boolean) Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-6 Map Reduce Map Operator Tree: TableScan - alias: y + alias: res:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:x + x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:x + x TableScan alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -2539,12 +3215,12 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col1 (type: string) + 0 value (type: string) + 1 value (type: string) Stage: Stage-5 Map Reduce @@ -2554,13 +3230,13 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3, _col4 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: value, key0, value0 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key0 (type: string), value (type: string), value0 (type: string) + outputColumnNames: key, value, value1 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2606,8 +3282,8 @@ POSTHOOK: Input: default@src1 POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Output: default@dest_j2 -POSTHOOK: Lineage: dest_j2.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j2.val2 SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j2.key SIMPLE [(src1)res:x.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j2.val2 SIMPLE [(src1)res:x.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j2.value SIMPLE [(srcpart)x.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from dest_j2 PREHOOK: type: QUERY @@ -2726,68 +3402,64 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:$hdt$_2:x + res:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:$hdt$_2:x + res:x TableScan - alias: x + alias: res:x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and value is not null) (type: boolean) Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-6 Map Reduce Map Operator Tree: TableScan - alias: y + alias: res:y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:y + y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:y + y TableScan alias: y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -2796,12 +3468,12 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col1 (type: string) + 0 value (type: string) + 1 value (type: string) Stage: Stage-5 Map Reduce @@ -2811,13 +3483,13 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3, _col4 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: value, key0, value0 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key0 (type: string), value (type: string), value0 (type: string) + outputColumnNames: key, value, value1 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2863,8 +3535,8 @@ POSTHOOK: Input: default@src1 POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Output: default@dest_j2 -POSTHOOK: Lineage: dest_j2.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j2.val2 SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j2.key SIMPLE [(src1)res:x.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j2.val2 SIMPLE [(src1)res:x.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j2.value SIMPLE [(srcpart)y.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from dest_j2 PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/join33.q.out b/ql/src/test/results/clientpositive/join33.q.out index afb373d..0f7dc8a 100644 --- a/ql/src/test/results/clientpositive/join33.q.out +++ b/ql/src/test/results/clientpositive/join33.q.out @@ -100,95 +100,141 @@ TOK_QUERY STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-6 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-6 - Stage-3 depends on stages: Stage-0 + Stage-7 is a root stage + Stage-5 depends on stages: Stage-7 + Stage-0 depends on stages: Stage-5 + Stage-2 depends on stages: Stage-0 STAGE PLANS: - Stage: Stage-8 + Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:y + x Fetch Operator limit: -1 - $hdt$_2:x + z Fetch Operator limit: -1 + Partition Description: + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart Alias -> Map Local Operator Tree: - $hdt$_0:y + x TableScan - alias: y - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: x + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col3 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Position of Big Table: 0 - $hdt$_2:x + z TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: z + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (value is not null and key is not null) (type: boolean) - Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - Position of Big Table: 0 + 0 value (type: string) + 1 value0 (type: string) + Position of Big Table: 1 - Stage: Stage-6 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan - alias: z + alias: y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0, value0 Position of Big Table: 0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col3, _col6 - Position of Big Table: 0 + 0 value (type: string) + 1 value0 (type: string) + outputColumnNames: value, value0, key0 + Position of Big Table: 1 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col3 (type: string), _col0 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key0 (type: string), value (type: string), value0 (type: string) + outputColumnNames: key, value, value1 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -356,7 +402,7 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:z] + /src [y] Stage: Stage-0 Move Operator @@ -380,7 +426,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 - Stage: Stage-3 + Stage: Stage-2 Stats-Aggr Operator #### A masked pattern was here #### diff --git a/ql/src/test/results/clientpositive/join34.q.out b/ql/src/test/results/clientpositive/join34.q.out index ffdf5a5..3b424a5 100644 --- a/ql/src/test/results/clientpositive/join34.q.out +++ b/ql/src/test/results/clientpositive/join34.q.out @@ -148,65 +148,65 @@ STAGE PLANS: Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:x + x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:x + x TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0)) and key is not null) (type: boolean) + predicate: (key is not null and ((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0))) (type: boolean) Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Position of Big Table: 0 Stage: Stage-5 Map Reduce Map Operator Tree: TableScan - alias: x + alias: null-subquery1:subq1-subquery1:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (UDFToDouble(key) < 20.0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) < 20.0) and ((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0))) (type: boolean) + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 220 Data size: 2336 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0, value0 Position of Big Table: 0 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 2569 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col3 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + expressions: key0 (type: string), value0 (type: string), value (type: string) + outputColumnNames: key, value, value1 + Statistics: Num rows: 242 Data size: 2569 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 2569 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -228,38 +228,38 @@ STAGE PLANS: GatherStats: true MultiFileSpray: false TableScan - alias: x + alias: null-subquery2:subq1-subquery2:x1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (UDFToDouble(key) > 100.0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) > 100.0) and ((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0))) (type: boolean) + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 220 Data size: 2336 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0, value0 Position of Big Table: 0 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 2569 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col3 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + expressions: key0 (type: string), value0 (type: string), value (type: string) + outputColumnNames: key, value, value1 + Statistics: Num rows: 242 Data size: 2569 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 2569 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -374,7 +374,7 @@ STAGE PLANS: name: default.src1 name: default.src1 Truncated Path -> Alias: - /src [$hdt$_0-subquery1:$hdt$_0-subquery1:x, $hdt$_0-subquery2:$hdt$_0-subquery2:x] + /src [null-subquery1:subq1-subquery1:x, null-subquery2:subq1-subquery2:x1] Stage: Stage-0 Move Operator @@ -427,7 +427,7 @@ POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@dest_j1 POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j1.val2 EXPRESSION [(src)x.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j1.val2 EXPRESSION [(src)null-subquery1:subq1-subquery1:x.FieldSchema(name:value, type:string, comment:default), (src)null-subquery2:subq1-subquery2:x1.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from dest_j1 PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/join35.q.out b/ql/src/test/results/clientpositive/join35.q.out index 5b68295..ee9f24d 100644 --- a/ql/src/test/results/clientpositive/join35.q.out +++ b/ql/src/test/results/clientpositive/join35.q.out @@ -159,28 +159,28 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: null-subquery1:subq1-subquery1:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (UDFToDouble(key) < 20.0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) < 20.0) and ((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0))) (type: boolean) + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -232,15 +232,15 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_0-subquery1:$hdt$_0-subquery1:$hdt$_0:x] + /src [null-subquery1:subq1-subquery1:x] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -250,7 +250,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1 + columns $f0,$f1 columns.types string,bigint escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -262,27 +262,27 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:x + x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:x + x TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0)) and key is not null) (type: boolean) + predicate: (key is not null and ((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0))) (type: boolean) Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 $f0 (type: string) + 1 key (type: string) Position of Big Table: 0 Stage: Stage-6 @@ -291,26 +291,26 @@ STAGE PLANS: TableScan GatherStats: false Union - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f1, key, value Position of Big Table: 0 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col3 (type: string), UDFToInteger(_col1) (type: int) + expressions: key (type: string), value (type: string), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -334,26 +334,26 @@ STAGE PLANS: TableScan GatherStats: false Union - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 + 0 $f0 (type: string) + 1 key (type: string) + outputColumnNames: $f1, key, value Position of Big Table: 0 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col3 (type: string), UDFToInteger(_col1) (type: int) + expressions: key (type: string), value (type: string), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -385,7 +385,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1 + columns $f0,$f1 columns.types string,bigint escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -394,7 +394,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1 + columns $f0,$f1 columns.types string,bigint escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -405,7 +405,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1 + columns $f0,$f1 columns.types string,bigint escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -414,7 +414,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1 + columns $f0,$f1 columns.types string,bigint escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -496,28 +496,28 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: null-subquery2:subq1-subquery2:x1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (UDFToDouble(key) > 100.0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) > 100.0) and ((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0))) (type: boolean) + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -569,32 +569,36 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_0-subquery2:$hdt$_0-subquery2:$hdt$_0:x] + /src [null-subquery2:subq1-subquery2:x1] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1 - columns.types string,bigint - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + outputColumnNames: $f0, $f1 + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns $f0,$f1 + columns.types string,bigint + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false PREHOOK: query: INSERT OVERWRITE TABLE dest_j1 SELECT x.key, x.value, subq1.cnt @@ -621,7 +625,7 @@ POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@dest_j1 POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j1.val2 EXPRESSION [(src)x.null, ] +POSTHOOK: Lineage: dest_j1.val2 EXPRESSION [(src)null-subquery1:subq1-subquery1:x.null, (src)null-subquery2:subq1-subquery2:x1.null, ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from dest_j1 PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/join38.q.out b/ql/src/test/results/clientpositive/join38.q.out index 3e94276..2cd11e0 100644 --- a/ql/src/test/results/clientpositive/join38.q.out +++ b/ql/src/test/results/clientpositive/join38.q.out @@ -90,18 +90,22 @@ STAGE PLANS: 1 '111' (type: string) outputColumnNames: _col1, _col10 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col1 (type: string), _col10 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: _col1 (type: string), _col10 (type: string) + outputColumnNames: _col1, _col10 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Group By Operator + aggregations: count(1) + keys: _col1 (type: string), _col10 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -111,13 +115,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/join4.q.out b/ql/src/test/results/clientpositive/join4.q.out index 9c3babe..1029768 100644 --- a/ql/src/test/results/clientpositive/join4.q.out +++ b/ql/src/test/results/clientpositive/join4.q.out @@ -50,48 +50,48 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: c:a:src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src1 + alias: c:b:src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string), UDFToInteger(key0) (type: int), value0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -148,10 +148,10 @@ INSERT OVERWRITE TABLE dest1 SELECT c.c1, c.c2, c.c3, c.c4 POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)c:a:src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)c:a:src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)c:b:src2.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)c:b:src2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git a/ql/src/test/results/clientpositive/join40.q.out b/ql/src/test/results/clientpositive/join40.q.out index 3b0d24f..fc8a12d 100644 --- a/ql/src/test/results/clientpositive/join40.q.out +++ b/ql/src/test/results/clientpositive/join40.q.out @@ -21,46 +21,50 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: x + alias: y:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) <= 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -659,21 +663,21 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -682,25 +686,25 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + expressions: key0 (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -3746,47 +3750,51 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f0) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -3800,15 +3808,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/join43.q.out b/ql/src/test/results/clientpositive/join43.q.out index f22a9b8..b08f466 100644 --- a/ql/src/test/results/clientpositive/join43.q.out +++ b/ql/src/test/results/clientpositive/join43.q.out @@ -294,18 +294,22 @@ STAGE PLANS: Filter Operator predicate: (_col3 > _col6) (type: boolean) Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col6) - keys: _col0 (type: string), _col3 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: _col0 (type: string), _col3 (type: int), _col6 (type: int) + outputColumnNames: _col0, _col3, _col6 Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: max(_col6) + keys: _col0 (type: string), _col3 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -331,12 +335,16 @@ STAGE PLANS: Filter Operator predicate: _col2 is not null (type: boolean) Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col2 (type: int) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -371,13 +379,17 @@ STAGE PLANS: 1 _col0 (type: string), _col3 (type: int) outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 28 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 28 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 28 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -512,18 +524,22 @@ STAGE PLANS: Filter Operator predicate: (_col3 > _col6) (type: boolean) Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col6) - keys: _col0 (type: string), _col3 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: _col0 (type: string), _col3 (type: int), _col6 (type: int) + outputColumnNames: _col0, _col3, _col6 Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: max(_col6) + keys: _col0 (type: string), _col3 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -545,12 +561,16 @@ STAGE PLANS: Filter Operator predicate: _col2 is not null (type: boolean) Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce diff --git a/ql/src/test/results/clientpositive/join5.q.out b/ql/src/test/results/clientpositive/join5.q.out index 0398655..eebca68 100644 --- a/ql/src/test/results/clientpositive/join5.q.out +++ b/ql/src/test/results/clientpositive/join5.q.out @@ -50,48 +50,48 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: c:a:src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 15.0)) and (UDFToDouble(key) < 25.0)) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src1 + alias: c:b:src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string), UDFToInteger(key0) (type: int), value0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -148,10 +148,10 @@ INSERT OVERWRITE TABLE dest1 SELECT c.c1, c.c2, c.c3, c.c4 POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)c:a:src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)c:a:src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)c:b:src2.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)c:b:src2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git a/ql/src/test/results/clientpositive/join6.q.out b/ql/src/test/results/clientpositive/join6.q.out index eab0fd8..a841f2d 100644 --- a/ql/src/test/results/clientpositive/join6.q.out +++ b/ql/src/test/results/clientpositive/join6.q.out @@ -50,48 +50,48 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: c:a:src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src1 + alias: c:b:src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string), UDFToInteger(key0) (type: int), value0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -148,10 +148,10 @@ INSERT OVERWRITE TABLE dest1 SELECT c.c1, c.c2, c.c3, c.c4 POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)c:a:src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)c:a:src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)c:b:src2.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)c:b:src2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git a/ql/src/test/results/clientpositive/join7.q.out b/ql/src/test/results/clientpositive/join7.q.out index 558b6f2..cd665b6 100644 --- a/ql/src/test/results/clientpositive/join7.q.out +++ b/ql/src/test/results/clientpositive/join7.q.out @@ -60,66 +60,66 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: c:a:src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src1 + alias: c:b:src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src1 + alias: c:c:src3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) > 20.0) and (UDFToDouble(key) < 25.0)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + predicate: ((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 20.0)) and (UDFToDouble(key) < 25.0)) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 Left Outer Join0 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: key, value, key0, value0, key1, value1 Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string), UDFToInteger(_col4) (type: int), _col5 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string), UDFToInteger(key0) (type: int), value0 (type: string), UDFToInteger(key1) (type: int), value1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -186,12 +186,12 @@ INSERT OVERWRITE TABLE dest1 SELECT c.c1, c.c2, c.c3, c.c4, c.c5, c.c6 POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c5 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c6 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)c:a:src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)c:a:src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)c:b:src2.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)c:b:src2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c5 EXPRESSION [(src)c:c:src3.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c6 SIMPLE [(src)c:c:src3.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git a/ql/src/test/results/clientpositive/join8.q.out b/ql/src/test/results/clientpositive/join8.q.out index 6ff3e33..3e823d4 100644 --- a/ql/src/test/results/clientpositive/join8.q.out +++ b/ql/src/test/results/clientpositive/join8.q.out @@ -50,51 +50,51 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: c:a:src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src1 + alias: c:b:src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col2 is null (type: boolean) + predicate: key0 is null (type: boolean) Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), null (type: int), _col3 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string), null (type: int), value0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -151,10 +151,10 @@ INSERT OVERWRITE TABLE dest1 SELECT c.c1, c.c2, c.c3, c.c4 where c.c3 IS NULL AN POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)c:a:src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)c:a:src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)c:b:src2.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)c:b:src2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git a/ql/src/test/results/clientpositive/join9.q.out b/ql/src/test/results/clientpositive/join9.q.out index 8421036..bf3e521 100644 --- a/ql/src/test/results/clientpositive/join9.q.out +++ b/ql/src/test/results/clientpositive/join9.q.out @@ -91,12 +91,12 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE tag: 0 auto parallelism: false @@ -110,15 +110,15 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -214,20 +214,20 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [$hdt$_1:src2] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:src1] + /src [src2] + /srcpart/ds=2008-04-08/hr=12 [src1] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col4 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col4 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/join_alt_syntax.q.out b/ql/src/test/results/clientpositive/join_alt_syntax.q.out index d119ab5..96fd634 100644 --- a/ql/src/test/results/clientpositive/join_alt_syntax.q.out +++ b/ql/src/test/results/clientpositive/join_alt_syntax.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [p1, p2]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select p1.p_name, p2.p_name from part p1 , part p2 PREHOOK: type: QUERY @@ -18,23 +18,23 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_name (type: string) - outputColumnNames: _col0 + outputColumnNames: p_name Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + value expressions: p_name (type: string) TableScan - alias: p1 + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_name (type: string) - outputColumnNames: _col0 + outputColumnNames: p_name Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + value expressions: p_name (type: string) Reduce Operator Tree: Join Operator condition map: @@ -42,15 +42,19 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1 + outputColumnNames: p_name, p_name0 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: p_name (type: string), p_name0 (type: string) + outputColumnNames: p_name, p_name0 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -77,66 +81,61 @@ STAGE PLANS: TableScan alias: p1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_name (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_name (type: string) + outputColumnNames: p_name + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE TableScan - alias: p1 + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_name (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_name (type: string) + outputColumnNames: p_name + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE TableScan - alias: p1 + alias: p3 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_name (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_name (type: string) + outputColumnNames: p_name + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 Inner Join 1 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 p_name (type: string) + 1 p_name (type: string) + 2 p_name (type: string) + outputColumnNames: p_name, p_name0, p_name1 + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_name (type: string), p_name0 (type: string), p_name1 (type: string) + outputColumnNames: p_name, p_name0, p_name1 + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -163,66 +162,61 @@ STAGE PLANS: TableScan alias: p1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_name (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_name (type: string) + outputColumnNames: p_name + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE TableScan - alias: p1 + alias: p2:part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_name (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_name (type: string) + outputColumnNames: p_name + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE TableScan - alias: p1 + alias: p3 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_name (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_name (type: string) + outputColumnNames: p_name + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 Inner Join 1 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 p_name (type: string) + 1 p_name (type: string) + 2 p_name (type: string) + outputColumnNames: p_name, p_name0, p_name1 + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_name (type: string), p_name0 (type: string), p_name1 (type: string) + outputColumnNames: p_name, p_name0, p_name1 + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -230,7 +224,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [p1, p2]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select p1.p_name, p2.p_name, p3.p_name from part p1 , part p2 , part p3 where p2.p_partkey + p1.p_partkey = p1.p_partkey and p3.p_name = p2.p_name @@ -253,26 +247,23 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: p_partkey, p_name Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string) + value expressions: p_partkey (type: int), p_name (type: string) TableScan - alias: p1 + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string) + outputColumnNames: p_partkey, p_name + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_name (type: string) Reduce Operator Tree: Join Operator condition map: @@ -280,63 +271,56 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: p_partkey, p_name, p_partkey0, p_name0 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col2 + _col0) = _col0) (type: boolean) + predicate: ((p_partkey0 + p_partkey) = p_partkey) (type: boolean) Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col3 (type: string) - outputColumnNames: _col1, _col3 - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: p_name0 (type: string) sort order: + - Map-reduce partition columns: _col3 (type: string) + Map-reduce partition columns: p_name0 (type: string) Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: p_name (type: string) TableScan - alias: p1 + alias: p3 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_name (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_name (type: string) + outputColumnNames: p_name + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col3, _col4 - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE + 0 p_name0 (type: string) + 1 p_name (type: string) + outputColumnNames: p_name, p_name0, p_name1 + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col3 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE + expressions: p_name (type: string), p_name0 (type: string), p_name1 (type: string) + outputColumnNames: p_name, p_name1, p_name2 + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -359,54 +343,48 @@ where p2.p_name = p3.p_name and p1.p_partkey = p4.p_partkey and p1.p_partkey = p2.p_partkey POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan alias: p1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (p_partkey is not null and p_name is not null) (type: boolean) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string) + outputColumnNames: p_partkey, p_name + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_partkey (type: int), p_name (type: string) + sort order: ++ + Map-reduce partition columns: p_partkey (type: int), p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE TableScan - alias: p1 + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (p_partkey is not null and p_name is not null) (type: boolean) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string) + outputColumnNames: p_partkey, p_name + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_partkey (type: int), p_name (type: string) + sort order: ++ + Map-reduce partition columns: p_partkey (type: int), p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int), _col1 (type: string) - 1 _col0 (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE + 0 p_partkey (type: int), p_name (type: string) + 1 p_partkey (type: int), p_name (type: string) + outputColumnNames: p_partkey, p_name, p_name0 + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -418,36 +396,33 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan + alias: p3 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_name (type: string) + outputColumnNames: p_name + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + TableScan Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: p_name0 (type: string) sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string) - TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_name (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: p_name0 (type: string) + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_name (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + 0 p_name (type: string) + 1 p_name0 (type: string) + outputColumnNames: p_name, p_partkey, p_name0, p_name00 + Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -455,48 +430,45 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-3 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan + alias: p4 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string) + outputColumnNames: p_partkey, p_name + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_partkey (type: int) + sort order: + + Map-reduce partition columns: p_partkey (type: int) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_name (type: string) + TableScan Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: p_partkey (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col3 (type: string), _col4 (type: string) - TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_partkey is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: p_partkey (type: int) + Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + value expressions: p_name (type: string), p_name0 (type: string), p_name00 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col4, _col6 - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE + 0 p_partkey (type: int) + 1 p_partkey (type: int) + outputColumnNames: p_name, p_name0, p_name00, p_name000 + Statistics: Num rows: 33 Data size: 4187 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col3 (type: string), _col4 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE + expressions: p_name00 (type: string), p_name000 (type: string), p_name0 (type: string), p_name (type: string) + outputColumnNames: p_name, p_name1, p_name2, p_name3 + Statistics: Num rows: 33 Data size: 4187 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 33 Data size: 4187 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -520,53 +492,52 @@ where p2.p_name = p3.p_name and p1.p_partkey = p4.p_partkey POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 + Stage-2 depends on stages: Stage-1, Stage-4 + Stage-4 is a root stage + Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: p1 + alias: p4 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string), _col0 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col0 (type: int) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string) + outputColumnNames: p_partkey, p_name + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_partkey (type: int) + sort order: + + Map-reduce partition columns: p_partkey (type: int) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_name (type: string) TableScan alias: p1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE + predicate: p_name is not null (type: boolean) + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: p_partkey, p_name + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string), _col0 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col0 (type: int) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE + key expressions: p_partkey (type: int) + sort order: + + Map-reduce partition columns: p_partkey (type: int) + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + value expressions: p_name (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string), _col0 (type: int) - 1 _col1 (type: string), _col0 (type: int) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE + 0 p_partkey (type: int) + 1 p_partkey (type: int) + outputColumnNames: p_name, p_partkey0, p_name0 + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -579,88 +550,88 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col3 (type: string) - sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string) + key expressions: p_name0 (type: string), p_partkey0 (type: int) + sort order: ++ + Map-reduce partition columns: p_name0 (type: string), p_partkey0 (type: int) + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + value expressions: p_name (type: string) TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_name (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string), p_partkey (type: int) + sort order: ++ + Map-reduce partition columns: p_name (type: string), p_partkey (type: int) + Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + value expressions: p_name0 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 0 p_name0 (type: string), p_partkey0 (type: int) + 1 p_name (type: string), p_partkey (type: int) + outputColumnNames: p_name, p_name0, p_name1, p_name00 + Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_name0 (type: string), p_name1 (type: string), p_name00 (type: string), p_name (type: string) + outputColumnNames: p_name, p_name1, p_name2, p_name3 + Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-3 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col3 (type: string), _col4 (type: string) - TableScan - alias: p1 + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: p_partkey is not null (type: boolean) + predicate: p_name is not null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: p_partkey, p_name Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: p_name (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int) + TableScan + alias: p3 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: p_name is not null (type: boolean) + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_name (type: string) + outputColumnNames: p_name + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col4, _col6 - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col3 (type: string), _col4 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 p_name (type: string) + 1 p_name (type: string) + outputColumnNames: p_partkey, p_name, p_name0 + Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_1.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_1.q.out index d565c7f..4ee761d 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_1.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_1.q.out @@ -20,64 +20,68 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: p_name (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: p_name (type: string) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan - alias: p1 + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p_name is not null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: p_name (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: p_name (type: string) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan - alias: p1 + alias: p3 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p_name is not null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: p_name (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: p_name (type: string) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 Inner Join 1 to 2 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - 2 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 + 0 p_name (type: string) + 1 p_name (type: string) + 2 p_name (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1 Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_partkey0 (type: int), p_name0 (type: string), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string), p_partkey1 (type: int), p_name1 (type: string), p_mfgr1 (type: string), p_brand1 (type: string), p_type1 (type: string), p_size1 (type: int), p_container1 (type: string), p_retailprice1 (type: double), p_comment1 (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1 Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -107,64 +111,68 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: p_name (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: p_name (type: string) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan - alias: p1 + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p_name is not null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: p_name (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: p_name (type: string) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan - alias: p1 + alias: p3 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p_name is not null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: p_name (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: p_name (type: string) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 Inner Join 1 to 2 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - 2 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 + 0 p_name (type: string) + 1 p_name (type: string) + 2 p_name (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1 Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_partkey0 (type: int), p_name0 (type: string), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string), p_partkey1 (type: int), p_name1 (type: string), p_mfgr1 (type: string), p_brand1 (type: string), p_type1 (type: string), p_size1 (type: int), p_container1 (type: string), p_retailprice1 (type: double), p_comment1 (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1 Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -172,7 +180,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[7][tables = [p1, p2]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select * from part p1 join part p2 join part p3 on p2.p_partkey + p1.p_partkey = p1.p_partkey and p3.p_name = p2.p_name PREHOOK: type: QUERY @@ -193,26 +201,26 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan - alias: p1 + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p_name is not null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) Reduce Operator Tree: Join Operator condition map: @@ -220,11 +228,11 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col9 + _col0) = _col0) (type: boolean) - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + predicate: (p_name0 is not null and ((p_partkey0 + p_partkey) = p_partkey)) (type: boolean) + Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -237,43 +245,47 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col10 (type: string) + key expressions: p_name0 (type: string) sort order: + - Map-reduce partition columns: _col10 (type: string) - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + Map-reduce partition columns: p_name0 (type: string) + Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_partkey0 (type: int), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string) TableScan - alias: p1 + alias: p3 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p_name is not null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: p_name (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: p_name (type: string) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col10 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 p_name0 (type: string) + 1 p_name (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1 + Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_partkey0 (type: int), p_name0 (type: string), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string), p_partkey1 (type: int), p_name1 (type: string), p_mfgr1 (type: string), p_brand1 (type: string), p_type1 (type: string), p_size1 (type: int), p_container1 (type: string), p_retailprice1 (type: double), p_comment1 (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1 + Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -281,7 +293,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[15][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[14][tables = [p1, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select * from part p1 join part p2 join part p3 on p2.p_partkey = 1 and p3.p_name = p2.p_name PREHOOK: type: QUERY @@ -289,54 +301,54 @@ POSTHOOK: query: explain select * from part p1 join part p2 join part p3 on p2.p_partkey = 1 and p3.p_name = p2.p_name POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: p1 + alias: p3 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p_name is not null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: p_name (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: p_name (type: string) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan - alias: p1 + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((p_partkey = 1) and p_name is not null) (type: boolean) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE + predicate: (p_name is not null and (p_partkey = 1)) (type: boolean) + Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE + expressions: p_brand (type: string), p_comment (type: string), p_container (type: string), p_mfgr (type: string), p_name (type: string), p_retailprice (type: double), p_size (type: int), p_type (type: string) + outputColumnNames: p_brand, p_comment, p_container, p_mfgr, p_name, p_retailprice, p_size, p_type + Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: p_name (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE + value expressions: 1 (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 + 0 p_name (type: string) + 1 p_name (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0 Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -345,25 +357,25 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) - TableScan alias: p1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_partkey0 (type: int), p_name0 (type: string), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string) Reduce Operator Tree: Join Operator condition map: @@ -371,11 +383,11 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey00, p_name00, p_mfgr00, p_brand00, p_type00, p_size00, p_container00, p_retailprice00, p_comment00 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), 1 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_partkey00 (type: int), p_name00 (type: string), p_mfgr00 (type: string), p_brand00 (type: string), p_type00 (type: string), p_size00 (type: int), p_container00 (type: string), p_retailprice00 (type: double), p_comment00 (type: string), p_partkey0 (type: int), p_name0 (type: string), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_2.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_2.q.out index 55c37e4..d08c0f6 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_2.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_2.q.out @@ -14,52 +14,55 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: p1 + alias: p3 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p_name is not null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: p_name (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: p_name (type: string) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan - alias: p1 + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p_name is not null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: p_name (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: p_name (type: string) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 + 0 p_name (type: string) + 1 p_name (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0 Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Filter Operator + predicate: p_name0 is not null (type: boolean) + Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce @@ -72,55 +75,55 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: p_name (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: p_name (type: string) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan - alias: p1 + alias: p4 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p_name is not null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: p_name (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: p_name (type: string) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: p_name0 (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + Map-reduce partition columns: p_name0 (type: string) + Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_partkey0 (type: int), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 + Inner Join 0 to 2 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - 2 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 30 Data size: 3806 Basic stats: COMPLETE Column stats: NONE + 0 p_name (type: string) + 1 p_name (type: string) + 2 p_name0 (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1, p_partkey00, p_name00, p_mfgr00, p_brand00, p_type00, p_size00, p_container00, p_retailprice00, p_comment00 + Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col27 (type: int), _col28 (type: string), _col29 (type: string), _col30 (type: string), _col31 (type: string), _col32 (type: int), _col33 (type: string), _col34 (type: double), _col35 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 30 Data size: 3806 Basic stats: COMPLETE Column stats: NONE + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_partkey00 (type: int), p_name00 (type: string), p_mfgr00 (type: string), p_brand00 (type: string), p_type00 (type: string), p_size00 (type: int), p_container00 (type: string), p_retailprice00 (type: double), p_comment00 (type: string), p_partkey1 (type: int), p_name1 (type: string), p_mfgr1 (type: string), p_brand1 (type: string), p_type1 (type: string), p_size1 (type: int), p_container1 (type: string), p_retailprice1 (type: double), p_comment1 (type: string), p_partkey0 (type: int), p_name0 (type: string), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1, p_partkey2, p_name2, p_mfgr2, p_brand2, p_type2, p_size2, p_container2, p_retailprice2, p_comment2 + Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 3806 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -142,55 +145,52 @@ from part p1 join part p2 join part p3 on p2.p_name = p1.p_name join part p4 on POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 + Stage-2 depends on stages: Stage-1, Stage-4 + Stage-4 is a root stage + Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: p1 + alias: p3 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (p_partkey is not null and p_name is not null) (type: boolean) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan - alias: p1 + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (p_partkey is not null and p_name is not null) (type: boolean) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE + predicate: p_partkey is not null (type: boolean) + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int), _col1 (type: string) - 1 _col0 (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE + 0 p_name (type: string) + 1 p_name (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0 + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -203,53 +203,58 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col10 (type: string) - sort order: + - Map-reduce partition columns: _col10 (type: string) - Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + key expressions: p_name0 (type: string), p_partkey0 (type: int) + sort order: ++ + Map-reduce partition columns: p_name0 (type: string), p_partkey0 (type: int) + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string) TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Reduce Output Operator + key expressions: p_name0 (type: string), p_partkey0 (type: int) + sort order: ++ + Map-reduce partition columns: p_name0 (type: string), p_partkey0 (type: int) + Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col10 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 0 p_name0 (type: string), p_partkey0 (type: int) + 1 p_name0 (type: string), p_partkey0 (type: int) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1, p_partkey00, p_name00, p_mfgr00, p_brand00, p_type00, p_size00, p_container00, p_retailprice00, p_comment00 + Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey00 (type: int), p_name00 (type: string), p_mfgr00 (type: string), p_brand00 (type: string), p_type00 (type: string), p_size00 (type: int), p_container00 (type: string), p_retailprice00 (type: double), p_comment00 (type: string), p_partkey0 (type: int), p_name0 (type: string), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string), p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_partkey1 (type: int), p_name1 (type: string), p_mfgr1 (type: string), p_brand1 (type: string), p_type1 (type: string), p_size1 (type: int), p_container1 (type: string), p_retailprice1 (type: double), p_comment1 (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1, p_partkey2, p_name2, p_mfgr2, p_brand2, p_type2, p_size2, p_container2, p_retailprice2, p_comment2 + Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-3 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string) + alias: p4 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: p_partkey is not null (type: boolean) + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_partkey (type: int) + sort order: + + Map-reduce partition columns: p_partkey (type: int) + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + value expressions: p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan alias: p1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE @@ -258,30 +263,29 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: p_partkey (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: p_partkey (type: int) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE + 0 p_partkey (type: int) + 1 p_partkey (type: int) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0 + Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out index 9077fc0..39ac56f 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out @@ -17,69 +17,64 @@ STAGE PLANS: TableScan alias: p1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan - alias: p1 + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan - alias: p1 + alias: p3 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 Inner Join 1 to 2 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - 2 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 p_name (type: string) + 1 p_name (type: string) + 2 p_name (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1 + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_partkey0 (type: int), p_name0 (type: string), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string), p_partkey1 (type: int), p_name1 (type: string), p_mfgr1 (type: string), p_brand1 (type: string), p_type1 (type: string), p_size1 (type: int), p_container1 (type: string), p_retailprice1 (type: double), p_comment1 (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1 + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -106,69 +101,64 @@ STAGE PLANS: TableScan alias: p1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan - alias: p1 + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan - alias: p1 + alias: p3 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 Inner Join 1 to 2 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - 2 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 p_name (type: string) + 1 p_name (type: string) + 2 p_name (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1 + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_partkey0 (type: int), p_name0 (type: string), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string), p_partkey1 (type: int), p_name1 (type: string), p_mfgr1 (type: string), p_brand1 (type: string), p_type1 (type: string), p_size1 (type: int), p_container1 (type: string), p_retailprice1 (type: double), p_comment1 (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1 + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -176,7 +166,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [p1, p2]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select * from part p1 join part p2 join part p3 where p2.p_partkey + p1.p_partkey = p1.p_partkey and p3.p_name = p2.p_name @@ -199,26 +189,23 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan - alias: p1 + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) Reduce Operator Tree: Join Operator condition map: @@ -226,10 +213,10 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col9 + _col0) = _col0) (type: boolean) + predicate: ((p_partkey0 + p_partkey) = p_partkey) (type: boolean) Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -243,43 +230,44 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col10 (type: string) + key expressions: p_name0 (type: string) sort order: + - Map-reduce partition columns: _col10 (type: string) + Map-reduce partition columns: p_name0 (type: string) Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + value expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_partkey0 (type: int), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string) TableScan - alias: p1 + alias: p3 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col10 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 p_name0 (type: string) + 1 p_name (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1 + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_partkey0 (type: int), p_name0 (type: string), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string), p_partkey1 (type: int), p_name1 (type: string), p_mfgr1 (type: string), p_brand1 (type: string), p_type1 (type: string), p_size1 (type: int), p_container1 (type: string), p_retailprice1 (type: double), p_comment1 (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1 + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -287,7 +275,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[15][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[12][tables = [p1, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select * from part p1 join part p2 join part p3 where p2.p_partkey = 1 and p3.p_name = p2.p_name @@ -297,55 +285,52 @@ from part p1 join part p2 join part p3 where p2.p_partkey = 1 and p3.p_name = p2.p_name POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: p1 + alias: p3 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + TableScan + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: p_name is not null (type: boolean) + predicate: (p_partkey = 1) (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + expressions: p_brand (type: string), p_comment (type: string), p_container (type: string), p_mfgr (type: string), p_name (type: string), p_retailprice (type: double), p_size (type: int), p_type (type: string) + outputColumnNames: p_brand, p_comment, p_container, p_mfgr, p_name, p_retailprice, p_size, p_type Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: p_name (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: p_name (type: string) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((p_partkey = 1) and p_name is not null) (type: boolean) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: 1 (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + 0 p_name (type: string) + 1 p_name (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0 + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -353,25 +338,25 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) - TableScan alias: p1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_partkey0 (type: int), p_name0 (type: string), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string) Reduce Operator Tree: Join Operator condition map: @@ -379,15 +364,15 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey00, p_name00, p_mfgr00, p_brand00, p_type00, p_size00, p_container00, p_retailprice00, p_comment00 + Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), 1 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_partkey00 (type: int), p_name00 (type: string), p_mfgr00 (type: string), p_brand00 (type: string), p_type00 (type: string), p_size00 (type: int), p_container00 (type: string), p_retailprice00 (type: double), p_comment00 (type: string), p_partkey0 (type: int), p_name0 (type: string), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1 + Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_4.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_4.q.out index 55e7678..bfdb8f6 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_4.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_4.q.out @@ -18,44 +18,38 @@ STAGE PLANS: TableScan alias: p1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan - alias: p1 + alias: p4 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + 0 p_name (type: string) + 1 p_name (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0 + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -67,62 +61,56 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: p1 + alias: p3 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan - alias: p1 + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: p_name (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_partkey0 (type: int), p_name0 (type: string), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 Inner Join 1 to 2 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - 2 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 30 Data size: 3806 Basic stats: COMPLETE Column stats: NONE + 0 p_name (type: string) + 1 p_name (type: string) + 2 p_name (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1, p_partkey00, p_name00, p_mfgr00, p_brand00, p_type00, p_size00, p_container00, p_retailprice00, p_comment00 + Statistics: Num rows: 61 Data size: 7614 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col27 (type: int), _col28 (type: string), _col29 (type: string), _col30 (type: string), _col31 (type: string), _col32 (type: int), _col33 (type: string), _col34 (type: double), _col35 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 30 Data size: 3806 Basic stats: COMPLETE Column stats: NONE + expressions: p_partkey1 (type: int), p_name1 (type: string), p_mfgr1 (type: string), p_brand1 (type: string), p_type1 (type: string), p_size1 (type: int), p_container1 (type: string), p_retailprice1 (type: double), p_comment1 (type: string), p_partkey0 (type: int), p_name0 (type: string), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string), p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_partkey00 (type: int), p_name00 (type: string), p_mfgr00 (type: string), p_brand00 (type: string), p_type00 (type: string), p_size00 (type: int), p_container00 (type: string), p_retailprice00 (type: double), p_comment00 (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1, p_partkey2, p_name2, p_mfgr2, p_brand2, p_type2, p_size2, p_container2, p_retailprice2, p_comment2 + Statistics: Num rows: 61 Data size: 7614 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 3806 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 61 Data size: 7614 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -145,56 +133,50 @@ where p2.p_name = p3.p_name and p1.p_partkey = p4.p_partkey and p1.p_partkey = p2.p_partkey POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan alias: p1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (p_partkey is not null and p_name is not null) (type: boolean) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_partkey (type: int), p_name (type: string) + sort order: ++ + Map-reduce partition columns: p_partkey (type: int), p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) TableScan - alias: p1 + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (p_partkey is not null and p_name is not null) (type: boolean) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_partkey (type: int), p_name (type: string) + sort order: ++ + Map-reduce partition columns: p_partkey (type: int), p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int), _col1 (type: string) - 1 _col0 (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE + 0 p_partkey (type: int), p_name (type: string) + 1 p_partkey (type: int), p_name (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0 + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -206,37 +188,34 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan + alias: p3 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_name (type: string) + sort order: + + Map-reduce partition columns: p_name (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + TableScan Reduce Output Operator - key expressions: _col10 (type: string) + key expressions: p_name0 (type: string) sort order: + - Map-reduce partition columns: _col10 (type: string) - Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) - TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Map-reduce partition columns: p_name0 (type: string) + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_partkey0 (type: int), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col10 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + 0 p_name (type: string) + 1 p_name0 (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey00, p_name00, p_mfgr00, p_brand00, p_type00, p_size00, p_container00, p_retailprice00, p_comment00 + Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -244,48 +223,49 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-3 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan + alias: p4 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: p_partkey (type: int) + sort order: + + Map-reduce partition columns: p_partkey (type: int) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + TableScan Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: p_partkey0 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string) - TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_partkey is not null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Map-reduce partition columns: p_partkey0 (type: int) + Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + value expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string), p_name0 (type: string), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string), p_partkey00 (type: int), p_name00 (type: string), p_mfgr00 (type: string), p_brand00 (type: string), p_type00 (type: string), p_size00 (type: int), p_container00 (type: string), p_retailprice00 (type: double), p_comment00 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 p_partkey (type: int) + 1 p_partkey0 (type: int) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey00, p_name00, p_mfgr00, p_brand00, p_type00, p_size00, p_container00, p_retailprice00, p_comment00, p_partkey000, p_name000, p_mfgr000, p_brand000, p_type000, p_size000, p_container000, p_retailprice000, p_comment000 + Statistics: Num rows: 33 Data size: 4187 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey00 (type: int), p_name00 (type: string), p_mfgr00 (type: string), p_brand00 (type: string), p_type00 (type: string), p_size00 (type: int), p_container00 (type: string), p_retailprice00 (type: double), p_comment00 (type: string), p_partkey000 (type: int), p_name000 (type: string), p_mfgr000 (type: string), p_brand000 (type: string), p_type000 (type: string), p_size000 (type: int), p_container000 (type: string), p_retailprice000 (type: double), p_comment000 (type: string), p_partkey0 (type: int), p_name0 (type: string), p_mfgr0 (type: string), p_brand0 (type: string), p_type0 (type: string), p_size0 (type: int), p_container0 (type: string), p_retailprice0 (type: double), p_comment0 (type: string), p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment, p_partkey0, p_name0, p_mfgr0, p_brand0, p_type0, p_size0, p_container0, p_retailprice0, p_comment0, p_partkey1, p_name1, p_mfgr1, p_brand1, p_type1, p_size1, p_container1, p_retailprice1, p_comment1, p_partkey2, p_name2, p_mfgr2, p_brand2, p_type2, p_size2, p_container2, p_retailprice2, p_comment2 + Statistics: Num rows: 33 Data size: 4187 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 33 Data size: 4187 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/join_filters.q.out b/ql/src/test/results/clientpositive/join_filters.q.out index 4f112bd..ae20e41 100644 --- a/ql/src/test/results/clientpositive/join_filters.q.out +++ b/ql/src/test/results/clientpositive/join_filters.q.out @@ -57,7 +57,7 @@ NULL NULL 12 35 NULL NULL 48 NULL NULL NULL NULL 40 LNZKrcVNAvaeDALnsg72bw== -Warning: Shuffle Join JOIN[6][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT * FROM myinput1 a FULL OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -807,7 +807,7 @@ POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 100 100 100 100 YaI1msgLVpfEx943Tfea/Q== -Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT * FROM myinput1 a FULL OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -817,7 +817,13 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 100 100 100 100 -YaI1msgLVpfEx943Tfea/Q== +12 35 NULL NULL +48 NULL NULL NULL +NULL 40 NULL NULL +NULL NULL 12 35 +NULL NULL 48 NULL +NULL NULL NULL 40 +JIHZKZaNhNR9LYBcRFyxng== PREHOOK: query: SELECT * FROM myinput1 a JOIN myinput1 b ON a.key = b.value AND a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git a/ql/src/test/results/clientpositive/join_merge_multi_expressions.q.out b/ql/src/test/results/clientpositive/join_merge_multi_expressions.q.out index b73643e..3bd6759 100644 --- a/ql/src/test/results/clientpositive/join_merge_multi_expressions.q.out +++ b/ql/src/test/results/clientpositive/join_merge_multi_expressions.q.out @@ -23,42 +23,42 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), hr (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), hr (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: key (type: string), hr (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE TableScan - alias: a + alias: b Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), hr (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), hr (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: key (type: string), hr (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE TableScan - alias: a + alias: c Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), hr (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: hr (type: string), key (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: hr (type: string), key (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator @@ -66,21 +66,23 @@ STAGE PLANS: Inner Join 0 to 1 Inner Join 0 to 2 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - 2 _col0 (type: string), _col1 (type: string) + 0 key (type: string), hr (type: string) + 1 key (type: string), hr (type: string) + 2 hr (type: string), key (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -94,15 +96,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -126,4 +132,4 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### -42464 +120 diff --git a/ql/src/test/results/clientpositive/join_merging.q.out b/ql/src/test/results/clientpositive/join_merging.q.out index b42bdc5..0423519 100644 --- a/ql/src/test/results/clientpositive/join_merging.q.out +++ b/ql/src/test/results/clientpositive/join_merging.q.out @@ -24,38 +24,38 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_size (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: p_partkey, p_size Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: p_partkey (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: p_partkey (type: int) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + value expressions: p_size (type: int) TableScan - alias: p1 + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_size (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: p_partkey, p_size Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: p_partkey (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: p_partkey (type: int) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + value expressions: p_size (type: int) TableScan - alias: p1 + alias: p3 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int) - outputColumnNames: _col0 + outputColumnNames: p_partkey Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: p_partkey (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: p_partkey (type: int) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator @@ -63,14 +63,14 @@ STAGE PLANS: Left Outer Join0 to 1 Right Outer Join1 to 2 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col1, _col3 + 0 p_partkey (type: int) + 1 p_partkey (type: int) + 2 p_partkey (type: int) + outputColumnNames: p_size, p_size0 Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int), _col3 (type: int) - outputColumnNames: _col0, _col1 + expressions: p_size (type: int), p_size0 (type: int) + outputColumnNames: p_size, p_size1 Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -113,80 +113,84 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_size (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: p_partkey, p_size Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: p_partkey (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: p_partkey (type: int) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + value expressions: p_size (type: int) TableScan - alias: p1 + alias: p2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_size (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: p_partkey, p_size Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: p_partkey (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: p_partkey (type: int) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + value expressions: p_size (type: int) Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 + 0 p_partkey (type: int) + 1 p_partkey (type: int) + outputColumnNames: p_size, p_partkey0, p_size0 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col1 > (_col3 + 10)) (type: boolean) + predicate: (p_size > (p_size0 + 10)) (type: boolean) Statistics: Num rows: 9 Data size: 1112 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: p_size (type: int), p_partkey0 (type: int), p_size0 (type: int) + outputColumnNames: p_size, p_partkey0, p_size0 + Statistics: Num rows: 9 Data size: 1112 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col2 (type: int) + key expressions: p_partkey0 (type: int) sort order: + - Map-reduce partition columns: _col2 (type: int) + Map-reduce partition columns: p_partkey0 (type: int) Statistics: Num rows: 9 Data size: 1112 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: int) + value expressions: p_size (type: int), p_size0 (type: int) TableScan - alias: p1 + alias: p3 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int) - outputColumnNames: _col0 + outputColumnNames: p_partkey Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: p_partkey (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: p_partkey (type: int) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3 + 0 p_partkey0 (type: int) + 1 p_partkey (type: int) + outputColumnNames: p_size, p_size0 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int), _col3 (type: int) - outputColumnNames: _col0, _col1 + expressions: p_size (type: int), p_size0 (type: int) + outputColumnNames: p_size, p_size1 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/join_nulls.q.out b/ql/src/test/results/clientpositive/join_nulls.q.out index b536985..f74c0ec 100644 --- a/ql/src/test/results/clientpositive/join_nulls.q.out +++ b/ql/src/test/results/clientpositive/join_nulls.q.out @@ -18,7 +18,7 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in1.txt' INTO TABLE my POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@myinput1 -Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT * FROM myinput1 a JOIN myinput1 b PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -36,7 +36,7 @@ POSTHOOK: Input: default@myinput1 NULL 35 100 100 NULL 35 48 NULL NULL 35 NULL 35 -Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT * FROM myinput1 a LEFT OUTER JOIN myinput1 b PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -54,7 +54,7 @@ POSTHOOK: Input: default@myinput1 NULL 35 100 100 NULL 35 48 NULL NULL 35 NULL 35 -Warning: Shuffle Join JOIN[6][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [a, b]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT * FROM myinput1 a RIGHT OUTER JOIN myinput1 b PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git a/ql/src/test/results/clientpositive/join_vc.q.out b/ql/src/test/results/clientpositive/join_vc.q.out index c0f11e7..f033dd7 100644 --- a/ql/src/test/results/clientpositive/join_vc.q.out +++ b/ql/src/test/results/clientpositive/join_vc.q.out @@ -159,21 +159,21 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: t2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: key, BLOCK__OFFSET__INSIDE__FILE Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: BLOCK__OFFSET__INSIDE__FILE (type: bigint) TableScan alias: t1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -182,25 +182,25 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: BLOCK__OFFSET__INSIDE__FILE Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 + expressions: BLOCK__OFFSET__INSIDE__FILE (type: bigint) + outputColumnNames: block__offset__inside__file Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -214,13 +214,13 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: bigint) + key expressions: block__offset__inside__file (type: bigint) sort order: + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: bigint) - outputColumnNames: _col0 + outputColumnNames: block__offset__inside__file Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/keyword_1.q.out b/ql/src/test/results/clientpositive/keyword_1.q.out index e215642..95e330a 100644 --- a/ql/src/test/results/clientpositive/keyword_1.q.out +++ b/ql/src/test/results/clientpositive/keyword_1.q.out @@ -33,7 +33,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: user (type: string) - outputColumnNames: _col0 + outputColumnNames: user Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE ListSink @@ -81,7 +81,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: role (type: string) - outputColumnNames: _col0 + outputColumnNames: role Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/lateral_view_cp.q.out b/ql/src/test/results/clientpositive/lateral_view_cp.q.out index 412595e..a601826 100644 --- a/ql/src/test/results/clientpositive/lateral_view_cp.q.out +++ b/ql/src/test/results/clientpositive/lateral_view_cp.q.out @@ -80,25 +80,8 @@ STAGE PLANS: Lateral View Join Operator outputColumnNames: _col2 Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col2) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Select Operator - expressions: _col1 (type: array) - outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - UDTF Operator - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - function name: explode - Lateral View Join Operator + Select Operator + expressions: _col2 (type: string) outputColumnNames: _col2 Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -112,6 +95,31 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col1 (type: array) + outputColumnNames: _col0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + function name: explode + Lateral View Join Operator + outputColumnNames: _col2 + Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: string) + outputColumnNames: _col2 + Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col2) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -127,13 +135,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/lateral_view_explode2.q.out b/ql/src/test/results/clientpositive/lateral_view_explode2.q.out index 65e268d..243fc53 100644 --- a/ql/src/test/results/clientpositive/lateral_view_explode2.q.out +++ b/ql/src/test/results/clientpositive/lateral_view_explode2.q.out @@ -26,24 +26,8 @@ STAGE PLANS: Lateral View Join Operator outputColumnNames: _col5, _col6 Statistics: Num rows: 1000 Data size: 200000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col5 (type: int), _col6 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator - expressions: array(1,2,3) (type: array) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 28000 Basic stats: COMPLETE Column stats: COMPLETE - UDTF Operator - Statistics: Num rows: 500 Data size: 28000 Basic stats: COMPLETE Column stats: COMPLETE - function name: explode - Lateral View Join Operator + Select Operator + expressions: _col5 (type: int), _col6 (type: int) outputColumnNames: _col5, _col6 Statistics: Num rows: 1000 Data size: 200000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator @@ -56,22 +40,50 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator + expressions: array(1,2,3) (type: array) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 28000 Basic stats: COMPLETE Column stats: COMPLETE + UDTF Operator + Statistics: Num rows: 500 Data size: 28000 Basic stats: COMPLETE Column stats: COMPLETE + function name: explode + Lateral View Join Operator + outputColumnNames: _col5, _col6 + Statistics: Num rows: 1000 Data size: 200000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col5 (type: int), _col6 (type: int) + outputColumnNames: _col5, _col6 + Statistics: Num rows: 1000 Data size: 200000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col5 (type: int), _col6 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Limit - Number of rows: 3 + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - File Output Operator - compressed: false + Limit + Number of rows: 3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/lateral_view_noalias.q.out b/ql/src/test/results/clientpositive/lateral_view_noalias.q.out index 90c9155..a6b0698 100644 --- a/ql/src/test/results/clientpositive/lateral_view_noalias.q.out +++ b/ql/src/test/results/clientpositive/lateral_view_noalias.q.out @@ -208,13 +208,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce diff --git a/ql/src/test/results/clientpositive/lateral_view_onview.q.out b/ql/src/test/results/clientpositive/lateral_view_onview.q.out index 8f576a5..932717a 100644 --- a/ql/src/test/results/clientpositive/lateral_view_onview.q.out +++ b/ql/src/test/results/clientpositive/lateral_view_onview.q.out @@ -57,11 +57,15 @@ STAGE PLANS: Lateral View Join Operator outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1000 Data size: 17000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col4 (type: int) - sort order: ++ + Select Operator + expressions: _col0 (type: string), _col1 (type: array), _col2 (type: int), _col3 (type: char(1)), _col4 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1000 Data size: 17000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: array), _col2 (type: int), _col3 (type: char(1)) + Reduce Output Operator + key expressions: _col0 (type: string), _col4 (type: int) + sort order: ++ + Statistics: Num rows: 1000 Data size: 17000 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: array), _col2 (type: int), _col3 (type: char(1)) Select Operator expressions: array(1,2,3) (type: array) outputColumnNames: _col0 @@ -72,11 +76,15 @@ STAGE PLANS: Lateral View Join Operator outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1000 Data size: 17000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col4 (type: int) - sort order: ++ + Select Operator + expressions: _col0 (type: string), _col1 (type: array), _col2 (type: int), _col3 (type: char(1)), _col4 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1000 Data size: 17000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: array), _col2 (type: int), _col3 (type: char(1)) + Reduce Output Operator + key expressions: _col0 (type: string), _col4 (type: int) + sort order: ++ + Statistics: Num rows: 1000 Data size: 17000 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: array), _col2 (type: int), _col3 (type: char(1)) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: array), VALUE._col1 (type: int), VALUE._col2 (type: char(1)), KEY.reducesinkkey1 (type: int) diff --git a/ql/src/test/results/clientpositive/limit0.q.out b/ql/src/test/results/clientpositive/limit0.q.out index 3f08bdd..1dd6af8 100644 --- a/ql/src/test/results/clientpositive/limit0.q.out +++ b/ql/src/test/results/clientpositive/limit0.q.out @@ -38,7 +38,20 @@ STAGE PLANS: Fetch Operator limit: 0 Processor Tree: - ListSink + TableScan + alias: sq1:src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 3 + Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + ListSink PREHOOK: query: select * from src where key = '238' limit 0 PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/limit_partition_metadataonly.q.out b/ql/src/test/results/clientpositive/limit_partition_metadataonly.q.out index 904acfc..2bff874 100644 --- a/ql/src/test/results/clientpositive/limit_partition_metadataonly.q.out +++ b/ql/src/test/results/clientpositive/limit_partition_metadataonly.q.out @@ -19,7 +19,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '2008-04-08' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink @@ -550,10 +550,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: string) - outputColumnNames: _col0 + outputColumnNames: hr Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: hr (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE @@ -566,15 +566,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: hr (type: string) + outputColumnNames: hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/limit_pushdown.q.out b/ql/src/test/results/clientpositive/limit_pushdown.q.out index d77bc60..8fb0af5 100644 --- a/ql/src/test/results/clientpositive/limit_pushdown.q.out +++ b/ql/src/test/results/clientpositive/limit_pushdown.q.out @@ -25,18 +25,18 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 @@ -102,18 +102,18 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 @@ -179,11 +179,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), (UDFToDouble(key) + 1.0) (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string) + aggregations: sum($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -199,18 +199,22 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: double) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 20 Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -267,11 +271,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), (UDFToDouble(key) + 1.0) (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col1) - keys: _col0 (type: string) + aggregations: avg($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -287,18 +291,22 @@ STAGE PLANS: aggregations: avg(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: double) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 20 Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -355,10 +363,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double) - outputColumnNames: _col0 + outputColumnNames: cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: double) + keys: cdouble (type: double) mode: hash outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -372,18 +380,22 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: double) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: cdouble Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: cdouble (type: double) + outputColumnNames: cdouble + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 20 Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -438,11 +450,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: tinyint), _col1 (type: double) + aggregations: count(DISTINCT cdouble) + keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -457,18 +469,22 @@ STAGE PLANS: aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: tinyint) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, $f1 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: ctinyint (type: tinyint), $f1 (type: bigint) + outputColumnNames: ctinyint, $f1 + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 20 Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -519,14 +535,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: alltypesorc + alias: t1:alltypesorc Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: tinyint), _col1 (type: double) + keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -539,24 +555,28 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: tinyint), KEY._col1 (type: double) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cdouble Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: tinyint) + aggregations: count(cdouble) + keys: ctinyint (type: tinyint) mode: complete - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, $f1 Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: ctinyint (type: tinyint), $f1 (type: bigint) + outputColumnNames: ctinyint, $f1 + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 20 Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -613,11 +633,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: ctinyint, cstring1, cstring2 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), count(DISTINCT _col2) - keys: _col0 (type: tinyint), _col1 (type: string), _col2 (type: string) + aggregations: count(DISTINCT cstring1), count(DISTINCT cstring2) + keys: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -632,18 +652,22 @@ STAGE PLANS: aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0) keys: KEY._col0 (type: tinyint) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: ctinyint, $f1, $f2 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: ctinyint (type: tinyint), $f1 (type: bigint), $f2 (type: bigint) + outputColumnNames: ctinyint, $f1, $f2 + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 20 Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -727,11 +751,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string) + aggregations: sum($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -746,29 +770,33 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: string), $f1 (type: double) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col1 (type: double) + key expressions: $f1 (type: double) sort order: + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 - value expressions: _col0 (type: string) + value expressions: $f0 (type: string) Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: double) - outputColumnNames: _col0, _col1 + expressions: VALUE.$f0 (type: string), KEY.reducesinkkey0 (type: double) + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 @@ -833,9 +861,8 @@ on subq.key=subq2.key limit 4 POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-4 + Stage-2 depends on stages: Stage-1, Stage-3 Stage-3 is a root stage - Stage-4 depends on stages: Stage-3 Stage-0 depends on stages: Stage-2 STAGE PLANS: @@ -843,15 +870,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: subq:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -867,71 +894,79 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 2 - Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 2 + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: $f0 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f0, $f1, $f00, $f10 Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 4 + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint), $f00 (type: string), $f10 (type: bigint) + outputColumnNames: $f0, $f1, $f00, $f10 Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Limit + Number of rows: 4 Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: src + alias: subq2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -947,37 +982,13 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.3 - value expressions: _col0 (type: string), _col1 (type: bigint) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col0 is not null (type: boolean) + predicate: $f0 is not null (type: boolean) Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1013,32 +1024,36 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 - value expressions: _col1 (type: string) + value expressions: $f1 (type: string) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: complete - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: double) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 20 Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1255,24 +1270,24 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: concat(key, value, value, value, value, value, value, value, value, value) (type: string), key (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: $f1 (type: string) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: complete - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: double) - outputColumnNames: _col0 + expressions: $f1 (type: double) + outputColumnNames: sum Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1286,14 +1301,14 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: double) + key expressions: sum (type: double) sort order: + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 2.0E-5 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: double) - outputColumnNames: _col0 + outputColumnNames: sum Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 diff --git a/ql/src/test/results/clientpositive/limit_pushdown_negative.q.out b/ql/src/test/results/clientpositive/limit_pushdown_negative.q.out index 2b6fb89..b1e5e59 100644 --- a/ql/src/test/results/clientpositive/limit_pushdown_negative.q.out +++ b/ql/src/test/results/clientpositive/limit_pushdown_negative.q.out @@ -20,49 +20,53 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 20 Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -113,16 +117,20 @@ STAGE PLANS: Filter Operator predicate: (_col1 > 100.0) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 20 Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -293,15 +301,19 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 20 + Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Move Operator diff --git a/ql/src/test/results/clientpositive/lineage1.q.out b/ql/src/test/results/clientpositive/lineage1.q.out index a655c6c..d3c4690 100644 --- a/ql/src/test/results/clientpositive/lineage1.q.out +++ b/ql/src/test/results/clientpositive/lineage1.q.out @@ -49,42 +49,42 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: p1 + alias: null-subquery1:j-subquery1:p1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: t1 + alias: null-subquery1:j-subquery1:t1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + expressions: key0 (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -100,7 +100,7 @@ STAGE PLANS: Union Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -115,7 +115,7 @@ STAGE PLANS: Union Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -183,42 +183,42 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: p1 + alias: null-subquery2:j-subquery2:p2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: t1 + alias: null-subquery2:j-subquery2:t2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + expressions: key0 (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -257,5 +257,5 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@dest_l1 -POSTHOOK: Lineage: dest_l1.key EXPRESSION [(src1)t1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_l1.value EXPRESSION [(src)p1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_l1.key EXPRESSION [(src1)null-subquery1:j-subquery1:t1.FieldSchema(name:key, type:string, comment:default), (src1)null-subquery2:j-subquery2:t2.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest_l1.value EXPRESSION [(src)null-subquery1:j-subquery1:p1.FieldSchema(name:value, type:string, comment:default), (src)null-subquery2:j-subquery2:p2.FieldSchema(name:value, type:string, comment:default), ] diff --git a/ql/src/test/results/clientpositive/lineage3.q.out b/ql/src/test/results/clientpositive/lineage3.q.out index 6fd2aa4..8ba4c00 100644 --- a/ql/src/test/results/clientpositive/lineage3.q.out +++ b/ql/src/test/results/clientpositive/lineage3.q.out @@ -10,7 +10,7 @@ insert into table d1 select x + length(y) PREHOOK: type: QUERY PREHOOK: Input: default@alltypesorc PREHOOK: Output: default@d1 -{"version":"1.0","engine":"mr","hash":"4c9b7b8d89403cef78668f15d393e542","queryText":"from (select a.ctinyint x, b.cstring1 y\nfrom alltypesorc a join alltypesorc b on a.cint = b.cbigint) t\ninsert into table d1 select x + length(y)","edges":[{"sources":[1,2],"targets":[0],"expression":"(UDFToInteger(a.ctinyint) + length(a.cstring1))","edgeType":"PROJECTION"},{"sources":[3,4],"targets":[0],"expression":"(UDFToLong(a.cint) = a.cbigint)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.d1.a"},{"id":1,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":2,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cstring1"},{"id":3,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cbigint"}]} +{"version":"1.0","engine":"mr","hash":"4c9b7b8d89403cef78668f15d393e542","queryText":"from (select a.ctinyint x, b.cstring1 y\nfrom alltypesorc a join alltypesorc b on a.cint = b.cbigint) t\ninsert into table d1 select x + length(y)","edges":[{"sources":[1,2],"targets":[0],"expression":"(UDFToInteger(t:a.ctinyint) + length(t:b.cstring1))","edgeType":"PROJECTION"},{"sources":[3],"targets":[0],"expression":"t:b.cbigint is not null","edgeType":"PREDICATE"},{"sources":[3,4],"targets":[0],"expression":"(t:b.cbigint = UDFToLong(t:a.cint))","edgeType":"PREDICATE"},{"sources":[4],"targets":[0],"expression":"t:a.cint is not null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.d1.a"},{"id":1,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":2,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cstring1"},{"id":3,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cbigint"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"}]} PREHOOK: query: drop table if exists d2 PREHOOK: type: DROPTABLE PREHOOK: query: create table d2(b varchar(128)) @@ -67,7 +67,7 @@ where cint > 10 and cint < 10000 limit 10 PREHOOK: type: QUERY PREHOOK: Input: default@alltypesorc #### A masked pattern was here #### -{"version":"1.0","engine":"mr","hash":"351b08ec58591554ec10a6ded68ef25f","queryText":"select cint, rank() over(order by cint) from alltypesorc\nwhere cint > 10 and cint < 10000 limit 10","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3,4,2,5,6,7,8,9,10,11,12,13],"targets":[1],"expression":"(tok_function rank (tok_windowspec (tok_partitioningspec (tok_distributeby 0) (tok_orderby (tok_tabsortcolnameasc (. (tok_table_or_col alltypesorc) cint)))) (tok_windowrange (preceding 2147483647) (following 2147483647))))","edgeType":"PROJECTION"},{"sources":[2],"targets":[0,1],"expression":"((alltypesorc.cint > 10) and (alltypesorc.cint < 10000))","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"cint"},{"id":1,"vertexType":"COLUMN","vertexId":"c1"},{"id":2,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"},{"id":3,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.csmallint"},{"id":5,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cbigint"},{"id":6,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cfloat"},{"id":7,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cdouble"},{"id":8,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cstring1"},{"id":9,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cstring2"},{"id":10,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctimestamp1"},{"id":11,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctimestamp2"},{"id":12,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cboolean1"},{"id":13,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cboolean2"}]} +{"version":"1.0","engine":"mr","hash":"351b08ec58591554ec10a6ded68ef25f","queryText":"select cint, rank() over(order by cint) from alltypesorc\nwhere cint > 10 and cint < 10000 limit 10","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[2],"targets":[1],"expression":"alltypesorc.$win$_col_9","edgeType":"PROJECTION"},{"sources":[2],"targets":[0,1],"expression":"((alltypesorc.cint > 10) and (alltypesorc.cint < 10000))","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"alltypesorc.cint"},{"id":1,"vertexType":"COLUMN","vertexId":"alltypesorc.rank_window_0"},{"id":2,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"}]} 762 1 762 1 762 1 @@ -86,7 +86,7 @@ order by a.ctinyint, a.cint PREHOOK: type: QUERY PREHOOK: Input: default@alltypesorc #### A masked pattern was here #### -{"version":"1.0","engine":"mr","hash":"40c3faa7abd1cdb7f12c1047a8a1d2ce","queryText":"select a.ctinyint, a.cint, count(a.cdouble)\n over(partition by a.ctinyint order by a.cint desc\n rows between 1 preceding and 1 following)\nfrom alltypesorc a inner join alltypesorc b on a.cint = b.cbigint\norder by a.ctinyint, a.cint","edges":[{"sources":[3],"targets":[0],"edgeType":"PROJECTION"},{"sources":[4],"targets":[1],"edgeType":"PROJECTION"},{"sources":[3,4,5,6],"targets":[2],"expression":"(tok_function count (. (tok_table_or_col $hdt$_0) cdouble) (tok_windowspec (tok_partitioningspec (tok_distributeby (. (tok_table_or_col $hdt$_0) ctinyint)) (tok_orderby (tok_tabsortcolnamedesc (. (tok_table_or_col $hdt$_0) cint)))) (tok_windowrange (preceding 1) (following 1))))","edgeType":"PROJECTION"},{"sources":[4,6],"targets":[0,1,2],"expression":"(UDFToLong(a.cint) = a.cbigint)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"a.ctinyint"},{"id":1,"vertexType":"COLUMN","vertexId":"a.cint"},{"id":2,"vertexType":"COLUMN","vertexId":"c2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"},{"id":5,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cdouble"},{"id":6,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cbigint"}]} +{"version":"1.0","engine":"mr","hash":"40c3faa7abd1cdb7f12c1047a8a1d2ce","queryText":"select a.ctinyint, a.cint, count(a.cdouble)\n over(partition by a.ctinyint order by a.cint desc\n rows between 1 preceding and 1 following)\nfrom alltypesorc a inner join alltypesorc b on a.cint = b.cbigint\norder by a.ctinyint, a.cint","edges":[{"sources":[3],"targets":[0],"edgeType":"PROJECTION"},{"sources":[4],"targets":[1],"edgeType":"PROJECTION"},{"sources":[5,3,4,6],"targets":[2],"expression":"$win$_col_10","edgeType":"PROJECTION"},{"sources":[5],"targets":[0,1,2],"expression":"b.cbigint is not null","edgeType":"PREDICATE"},{"sources":[5,4],"targets":[0,1,2],"expression":"(b.cbigint = UDFToLong(a.cint))","edgeType":"PREDICATE"},{"sources":[4],"targets":[0,1,2],"expression":"a.cint is not null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"$hdt$_0.ctinyint"},{"id":1,"vertexType":"COLUMN","vertexId":"$hdt$_0.cint"},{"id":2,"vertexType":"COLUMN","vertexId":"$hdt$_0._o__col31"},{"id":3,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"},{"id":5,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cbigint"},{"id":6,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cdouble"}]} PREHOOK: query: with v2 as (select cdouble, count(cint) over() a, sum(cint + cbigint) over(partition by cboolean1) b @@ -97,7 +97,7 @@ order by cdouble, a, b limit 5 PREHOOK: type: QUERY PREHOOK: Input: default@alltypesorc #### A masked pattern was here #### -{"version":"1.0","engine":"mr","hash":"a083a5322b6a83af6f614f299d0361e4","queryText":"with v2 as\n (select cdouble, count(cint) over() a,\n sum(cint + cbigint) over(partition by cboolean1) b\n from (select * from alltypesorc) v1)\nselect cdouble, a, b, a + b, cdouble + a from v2\nwhere cdouble is not null\norder by cdouble, a, b limit 5","edges":[{"sources":[5],"targets":[0],"edgeType":"PROJECTION"},{"sources":[6,7,8,9,10,5,11,12,13,14,15,16],"targets":[1],"expression":"(tok_function count (. (tok_table_or_col alltypesorc) cint) (tok_windowspec (tok_partitioningspec (tok_distributeby 0) (tok_orderby (tok_tabsortcolnameasc 0))) (tok_windowrange (preceding 2147483647) (following 2147483647))))","edgeType":"PROJECTION"},{"sources":[6,7,8,9,10,5,11,12,13,14,15,16],"targets":[2],"expression":"(tok_function sum (+ (tok_function tok_bigint (. (tok_table_or_col alltypesorc) cint)) (. (tok_table_or_col alltypesorc) cbigint)) (tok_windowspec (tok_partitioningspec (tok_distributeby (. (tok_table_or_col alltypesorc) cboolean1)) (tok_orderby (tok_tabsortcolnameasc (. (tok_table_or_col alltypesorc) cboolean1)))) (tok_windowrange (preceding 2147483647) (following 2147483647))))","edgeType":"PROJECTION"},{"sources":[6,7,8,9,10,5,11,12,13,14,15,16],"targets":[3],"expression":"((tok_function count (. (tok_table_or_col alltypesorc) cint) (tok_windowspec (tok_partitioningspec (tok_distributeby 0) (tok_orderby (tok_tabsortcolnameasc 0))) (tok_windowrange (preceding 2147483647) (following 2147483647)))) + (tok_function sum (+ (tok_function tok_bigint (. (tok_table_or_col alltypesorc) cint)) (. (tok_table_or_col alltypesorc) cbigint)) (tok_windowspec (tok_partitioningspec (tok_distributeby (. (tok_table_or_col alltypesorc) cboolean1)) (tok_orderby (tok_tabsortcolnameasc (. (tok_table_or_col alltypesorc) cboolean1)))) (tok_windowrange (preceding 2147483647) (following 2147483647)))))","edgeType":"PROJECTION"},{"sources":[5,6,7,8,9,10,11,12,13,14,15,16],"targets":[4],"expression":"(alltypesorc.cdouble + UDFToDouble((tok_function count (. (tok_table_or_col alltypesorc) cint) (tok_windowspec (tok_partitioningspec (tok_distributeby 0) (tok_orderby (tok_tabsortcolnameasc 0))) (tok_windowrange (preceding 2147483647) (following 2147483647))))))","edgeType":"PROJECTION"},{"sources":[5],"targets":[0,1,2,3,4],"expression":"alltypesorc.cdouble is not null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"cdouble"},{"id":1,"vertexType":"COLUMN","vertexId":"a"},{"id":2,"vertexType":"COLUMN","vertexId":"b"},{"id":3,"vertexType":"COLUMN","vertexId":"c3"},{"id":4,"vertexType":"COLUMN","vertexId":"c4"},{"id":5,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cdouble"},{"id":6,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":7,"vertexType":"COLUMN","vertexId":"default.alltypesorc.csmallint"},{"id":8,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"},{"id":9,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cbigint"},{"id":10,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cfloat"},{"id":11,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cstring1"},{"id":12,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cstring2"},{"id":13,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctimestamp1"},{"id":14,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctimestamp2"},{"id":15,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cboolean1"},{"id":16,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cboolean2"}]} +{"version":"1.0","engine":"mr","hash":"a083a5322b6a83af6f614f299d0361e4","queryText":"with v2 as\n (select cdouble, count(cint) over() a,\n sum(cint + cbigint) over(partition by cboolean1) b\n from (select * from alltypesorc) v1)\nselect cdouble, a, b, a + b, cdouble + a from v2\nwhere cdouble is not null\norder by cdouble, a, b limit 5","edges":[{"sources":[5],"targets":[0],"edgeType":"PROJECTION"},{"sources":[6,7,8,9,10,5,11,12,13,14,15,16],"targets":[1],"expression":"VALUE.$win$_col_11","edgeType":"PROJECTION"},{"sources":[6,7,8,9,10,5,11,12,13,14,15,16],"targets":[2],"expression":"v2:v1:alltypesorc.$win$_col_12","edgeType":"PROJECTION"},{"sources":[6,7,8,9,10,5,11,12,13,14,15,16],"targets":[3],"expression":"(v2:v1:alltypesorc.count_window_0 + v2:v1:alltypesorc.sum_window_1)","edgeType":"PROJECTION"},{"sources":[5,6,7,8,9,10,11,12,13,14,15,16],"targets":[4],"expression":"(v2:v1:alltypesorc.cdouble + UDFToDouble(v2:v1:alltypesorc.count_window_0))","edgeType":"PROJECTION"},{"sources":[5],"targets":[0,1,2,3,4],"expression":"v2:v1:alltypesorc.cdouble is not null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"v2.cdouble"},{"id":1,"vertexType":"COLUMN","vertexId":"v2.a"},{"id":2,"vertexType":"COLUMN","vertexId":"v2.b"},{"id":3,"vertexType":"COLUMN","vertexId":"v2._o__c3"},{"id":4,"vertexType":"COLUMN","vertexId":"v2._o__c4"},{"id":5,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cdouble"},{"id":6,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":7,"vertexType":"COLUMN","vertexId":"default.alltypesorc.csmallint"},{"id":8,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"},{"id":9,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cbigint"},{"id":10,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cfloat"},{"id":11,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cstring1"},{"id":12,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cstring2"},{"id":13,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctimestamp1"},{"id":14,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctimestamp2"},{"id":15,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cboolean1"},{"id":16,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cboolean2"}]} -16379.0 9173 -919551973060 -919551963887 -7206.0 -16373.0 9173 -919551973060 -919551963887 -7200.0 -16372.0 9173 -919551973060 -919551963887 -7199.0 @@ -116,7 +116,7 @@ order by a.cbigint, a.ctinyint, b.cint, b.ctinyint limit 5 PREHOOK: type: QUERY PREHOOK: Input: default@alltypesorc #### A masked pattern was here #### -{"version":"1.0","engine":"mr","hash":"afd760470fc5aa6d3e8348dee03af97f","queryText":"select a.cbigint, a.ctinyint, b.cint, b.ctinyint\nfrom\n (select ctinyint, cbigint from alltypesorc\n union all\n select ctinyint, cbigint from alltypesorc) a\n inner join\n alltypesorc b\n on (a.ctinyint = b.ctinyint)\nwhere b.ctinyint < 100 and a.cbigint is not null and b.cint is not null\norder by a.cbigint, a.ctinyint, b.cint, b.ctinyint limit 5","edges":[{"sources":[4],"targets":[0],"expression":"cbigint","edgeType":"PROJECTION"},{"sources":[5],"targets":[1],"expression":"ctinyint","edgeType":"PROJECTION"},{"sources":[6],"targets":[2],"edgeType":"PROJECTION"},{"sources":[5],"targets":[3],"edgeType":"PROJECTION"},{"sources":[4],"targets":[0,1,2,3],"expression":"alltypesorc.cbigint is not null","edgeType":"PREDICATE"},{"sources":[5],"targets":[0,1,2,3],"expression":"(ctinyint < 100)","edgeType":"PREDICATE"},{"sources":[5],"targets":[0,1,2,3],"expression":"(ctinyint = alltypesorc.ctinyint)","edgeType":"PREDICATE"},{"sources":[5,6],"targets":[0,1,2,3],"expression":"((alltypesorc.ctinyint < 100) and alltypesorc.cint is not null)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"a.cbigint"},{"id":1,"vertexType":"COLUMN","vertexId":"a.ctinyint"},{"id":2,"vertexType":"COLUMN","vertexId":"b.cint"},{"id":3,"vertexType":"COLUMN","vertexId":"b.ctinyint"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cbigint"},{"id":5,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":6,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"}]} +{"version":"1.0","engine":"mr","hash":"afd760470fc5aa6d3e8348dee03af97f","queryText":"select a.cbigint, a.ctinyint, b.cint, b.ctinyint\nfrom\n (select ctinyint, cbigint from alltypesorc\n union all\n select ctinyint, cbigint from alltypesorc) a\n inner join\n alltypesorc b\n on (a.ctinyint = b.ctinyint)\nwhere b.ctinyint < 100 and a.cbigint is not null and b.cint is not null\norder by a.cbigint, a.ctinyint, b.cint, b.ctinyint limit 5","edges":[{"sources":[4],"targets":[0],"expression":"cbigint","edgeType":"PROJECTION"},{"sources":[5],"targets":[1],"expression":"ctinyint","edgeType":"PROJECTION"},{"sources":[6],"targets":[2],"edgeType":"PROJECTION"},{"sources":[5],"targets":[3],"edgeType":"PROJECTION"},{"sources":[5],"targets":[0,1,2,3],"expression":"null-subquery1:a-subquery1:alltypesorc.ctinyint is not null","edgeType":"PREDICATE"},{"sources":[4],"targets":[0,1,2,3],"expression":"null-subquery1:a-subquery1:alltypesorc.cbigint is not null","edgeType":"PREDICATE"},{"sources":[5],"targets":[0,1,2,3],"expression":"null-subquery2:a-subquery2:alltypesorc.ctinyint is not null","edgeType":"PREDICATE"},{"sources":[4],"targets":[0,1,2,3],"expression":"null-subquery2:a-subquery2:alltypesorc.cbigint is not null","edgeType":"PREDICATE"},{"sources":[5],"targets":[0,1,2,3],"expression":"(ctinyint < 100)","edgeType":"PREDICATE"},{"sources":[5],"targets":[0,1,2,3],"expression":"(ctinyint = b.ctinyint)","edgeType":"PREDICATE"},{"sources":[5],"targets":[0,1,2,3],"expression":"b.ctinyint is not null","edgeType":"PREDICATE"},{"sources":[5,6],"targets":[0,1,2,3],"expression":"((b.ctinyint < 100) and b.cint is not null)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"$hdt$_0.cbigint"},{"id":1,"vertexType":"COLUMN","vertexId":"$hdt$_0.ctinyint"},{"id":2,"vertexType":"COLUMN","vertexId":"$hdt$_0.cint"},{"id":3,"vertexType":"COLUMN","vertexId":"$hdt$_0.ctinyint1"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cbigint"},{"id":5,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":6,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"}]} -2147311592 -51 -1071480828 -51 -2147311592 -51 -1071480828 -51 -2147311592 -51 -1067683781 -51 @@ -135,7 +135,7 @@ and x.ctinyint + length(c.cstring2) < 1000 PREHOOK: type: QUERY PREHOOK: Input: default@alltypesorc #### A masked pattern was here #### -{"version":"1.0","engine":"mr","hash":"3a12ad24b2622a8958df12d0bdc60f8a","queryText":"select x.ctinyint, x.cint, c.cbigint-100, c.cstring1\nfrom alltypesorc c\njoin (\n select a.ctinyint ctinyint, b.cint cint\n from (select * from alltypesorc a where cboolean1=false) a\n join alltypesorc b on (a.cint = b.cbigint - 224870380)\n ) x on (x.cint = c.cint)\nwhere x.ctinyint > 10\nand x.cint < 4.5\nand x.ctinyint + length(c.cstring2) < 1000","edges":[{"sources":[4],"targets":[0],"edgeType":"PROJECTION"},{"sources":[5],"targets":[1],"edgeType":"PROJECTION"},{"sources":[6],"targets":[2],"expression":"(c.cbigint - UDFToLong(100))","edgeType":"PROJECTION"},{"sources":[7],"targets":[3],"edgeType":"PROJECTION"},{"sources":[5],"targets":[0,1,2,3],"expression":"(UDFToDouble(c.cint) < 4.5)","edgeType":"PREDICATE"},{"sources":[5],"targets":[0,1,2,3],"expression":"(c.cint = c.cint)","edgeType":"PREDICATE"},{"sources":[6,5],"targets":[0,1,2,3],"expression":"((c.cbigint - UDFToLong(224870380)) = UDFToLong(c.cint))","edgeType":"PREDICATE"},{"sources":[8],"targets":[0,1,2,3],"expression":"(c.cboolean1 = false)","edgeType":"PREDICATE"},{"sources":[4],"targets":[0,1,2,3],"expression":"(c.ctinyint > 10)","edgeType":"PREDICATE"},{"sources":[4,9],"targets":[0,1,2,3],"expression":"((UDFToInteger(c.ctinyint) + length(c.cstring2)) < 1000)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"x.ctinyint"},{"id":1,"vertexType":"COLUMN","vertexId":"x.cint"},{"id":2,"vertexType":"COLUMN","vertexId":"c2"},{"id":3,"vertexType":"COLUMN","vertexId":"c.cstring1"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":5,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"},{"id":6,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cbigint"},{"id":7,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cstring1"},{"id":8,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cboolean1"},{"id":9,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cstring2"}]} +{"version":"1.0","engine":"mr","hash":"3a12ad24b2622a8958df12d0bdc60f8a","queryText":"select x.ctinyint, x.cint, c.cbigint-100, c.cstring1\nfrom alltypesorc c\njoin (\n select a.ctinyint ctinyint, b.cint cint\n from (select * from alltypesorc a where cboolean1=false) a\n join alltypesorc b on (a.cint = b.cbigint - 224870380)\n ) x on (x.cint = c.cint)\nwhere x.ctinyint > 10\nand x.cint < 4.5\nand x.ctinyint + length(c.cstring2) < 1000","edges":[{"sources":[4],"targets":[0],"edgeType":"PROJECTION"},{"sources":[5],"targets":[1],"edgeType":"PROJECTION"},{"sources":[6],"targets":[2],"expression":"(c.cbigint - UDFToLong(100))","edgeType":"PROJECTION"},{"sources":[7],"targets":[3],"edgeType":"PROJECTION"},{"sources":[5],"targets":[0,1,2,3],"expression":"c.cint is not null","edgeType":"PREDICATE"},{"sources":[5],"targets":[0,1,2,3],"expression":"(UDFToDouble(c.cint) < 4.5)","edgeType":"PREDICATE"},{"sources":[5],"targets":[0,1,2,3],"expression":"(c.cint = x:b.cint)","edgeType":"PREDICATE"},{"sources":[8],"targets":[0,1,2,3],"expression":"(x:a:a.cboolean1 = false)","edgeType":"PREDICATE"},{"sources":[5],"targets":[0,1,2,3],"expression":"x:a:a.cint is not null","edgeType":"PREDICATE"},{"sources":[4],"targets":[0,1,2,3],"expression":"(x:a:a.ctinyint > 10)","edgeType":"PREDICATE"},{"sources":[5,6],"targets":[0,1,2,3],"expression":"(UDFToLong(x:a:a.cint) = (x:b.cbigint - UDFToLong(224870380)))","edgeType":"PREDICATE"},{"sources":[6],"targets":[0,1,2,3],"expression":"x:b.cbigint is not null","edgeType":"PREDICATE"},{"sources":[5],"targets":[0,1,2,3],"expression":"x:b.cint is not null","edgeType":"PREDICATE"},{"sources":[5],"targets":[0,1,2,3],"expression":"(UDFToDouble(x:b.cint) < 4.5)","edgeType":"PREDICATE"},{"sources":[4,9],"targets":[0,1,2,3],"expression":"((UDFToInteger(x:a:a.ctinyint) + length(c.cstring2)) < 1000)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"$hdt$_0.ctinyint"},{"id":1,"vertexType":"COLUMN","vertexId":"$hdt$_0.cint"},{"id":2,"vertexType":"COLUMN","vertexId":"$hdt$_0._o__c2"},{"id":3,"vertexType":"COLUMN","vertexId":"$hdt$_0.cstring1"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":5,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"},{"id":6,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cbigint"},{"id":7,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cstring1"},{"id":8,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cboolean1"},{"id":9,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cstring2"}]} 11 -654374827 857266369 OEfPnHnIYueoup PREHOOK: query: select c1, x2, x3 from ( @@ -158,7 +158,7 @@ order by x2, c1 desc PREHOOK: type: QUERY PREHOOK: Input: default@alltypesorc #### A masked pattern was here #### -{"version":"1.0","engine":"mr","hash":"bc64f8bec21631969a17930ec609cde9","queryText":"select c1, x2, x3\nfrom (\n select c1, min(c2) x2, sum(c3) x3\n from (\n select c1, c2, c3\n from (\n select cint c1, ctinyint c2, min(cbigint) c3\n from alltypesorc\n where cint is not null\n group by cint, ctinyint\n order by cint, ctinyint\n limit 5\n ) x\n ) x2\n group by c1\n) y\nwhere x2 > 0\norder by x2, c1 desc","edges":[{"sources":[3],"targets":[0],"edgeType":"PROJECTION"},{"sources":[4],"targets":[1],"expression":"min(default.alltypesorc.ctinyint)","edgeType":"PROJECTION"},{"sources":[5],"targets":[2],"expression":"sum(min(default.alltypesorc.cbigint))","edgeType":"PROJECTION"},{"sources":[3],"targets":[0,1,2],"expression":"alltypesorc.cint is not null","edgeType":"PREDICATE"},{"sources":[4],"targets":[0,1,2],"expression":"(min(default.alltypesorc.ctinyint) > 0)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"c1"},{"id":1,"vertexType":"COLUMN","vertexId":"x2"},{"id":2,"vertexType":"COLUMN","vertexId":"x3"},{"id":3,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":5,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cbigint"}]} +{"version":"1.0","engine":"mr","hash":"bc64f8bec21631969a17930ec609cde9","queryText":"select c1, x2, x3\nfrom (\n select c1, min(c2) x2, sum(c3) x3\n from (\n select c1, c2, c3\n from (\n select cint c1, ctinyint c2, min(cbigint) c3\n from alltypesorc\n where cint is not null\n group by cint, ctinyint\n order by cint, ctinyint\n limit 5\n ) x\n ) x2\n group by c1\n) y\nwhere x2 > 0\norder by x2, c1 desc","edges":[{"sources":[3],"targets":[0],"edgeType":"PROJECTION"},{"sources":[4],"targets":[1],"expression":"min(default.alltypesorc.ctinyint)","edgeType":"PROJECTION"},{"sources":[5],"targets":[2],"expression":"sum(min(default.alltypesorc.cbigint))","edgeType":"PROJECTION"},{"sources":[3],"targets":[0,1,2],"expression":"y:x2:x:alltypesorc.cint is not null","edgeType":"PREDICATE"},{"sources":[4],"targets":[0,1,2],"expression":"(min(default.alltypesorc.ctinyint) > 0)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"y.$f0"},{"id":1,"vertexType":"COLUMN","vertexId":"y.$f1"},{"id":2,"vertexType":"COLUMN","vertexId":"y.$f2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":5,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cbigint"}]} -1072910839 11 2048385991 -1073279343 11 -1595604468 PREHOOK: query: select key, value from src1 @@ -166,7 +166,7 @@ where key in (select key+18 from src1) order by key PREHOOK: type: QUERY PREHOOK: Input: default@src1 #### A masked pattern was here #### -{"version":"1.0","engine":"mr","hash":"8b9d63653e36ecf4dd425d3cc3de9199","queryText":"select key, value from src1\nwhere key in (select key+18 from src1) order by key","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[],"targets":[0,1],"expression":"(1 = 1)","edgeType":"PREDICATE"},{"sources":[2],"targets":[0,1],"expression":"(UDFToDouble(src1.key) = (UDFToDouble(src1.key) + UDFToDouble(18)))","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"key"},{"id":1,"vertexType":"COLUMN","vertexId":"value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"}]} +{"version":"1.0","engine":"mr","hash":"8b9d63653e36ecf4dd425d3cc3de9199","queryText":"select key, value from src1\nwhere key in (select key+18 from src1) order by key","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2],"targets":[0,1],"expression":"UDFToDouble(src1.key) is not null","edgeType":"PREDICATE"},{"sources":[],"targets":[0,1],"expression":"(1 = 1)","edgeType":"PREDICATE"},{"sources":[2],"targets":[0,1],"expression":"(UDFToDouble(src1.EXPR$0) = sq_1:src1._o__c0)","edgeType":"PREDICATE"},{"sources":[2],"targets":[0,1],"expression":"(UDFToDouble(sq_1:src1.key) + UDFToDouble(18)) is not null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"$hdt$_0.key"},{"id":1,"vertexType":"COLUMN","vertexId":"$hdt$_0.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"}]} 146 val_146 273 val_273 PREHOOK: query: select * from src1 a @@ -178,15 +178,15 @@ PREHOOK: type: QUERY PREHOOK: Input: default@alltypesorc PREHOOK: Input: default@src1 #### A masked pattern was here #### -{"version":"1.0","engine":"mr","hash":"8bf193b0658183be94e2428a79d91d10","queryText":"select * from src1 a\nwhere exists\n (select cint from alltypesorc b\n where a.key = b.ctinyint + 300)\nand key > 300","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2],"targets":[0,1],"expression":"(UDFToDouble(a.key) > UDFToDouble(300))","edgeType":"PREDICATE"},{"sources":[2,4],"targets":[0,1],"expression":"(UDFToDouble(a.key) = UDFToDouble((UDFToInteger(b.ctinyint) + 300)))","edgeType":"PREDICATE"},{"sources":[],"targets":[0,1],"expression":"(1 = 1)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"a.key"},{"id":1,"vertexType":"COLUMN","vertexId":"a.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"}]} +{"version":"1.0","engine":"mr","hash":"8bf193b0658183be94e2428a79d91d10","queryText":"select * from src1 a\nwhere exists\n (select cint from alltypesorc b\n where a.key = b.ctinyint + 300)\nand key > 300","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2],"targets":[0,1],"expression":"UDFToDouble(a.key) is not null","edgeType":"PREDICATE"},{"sources":[2],"targets":[0,1],"expression":"(UDFToDouble(a.key) > UDFToDouble(300))","edgeType":"PREDICATE"},{"sources":[2,4],"targets":[0,1],"expression":"(UDFToDouble(a.EXPR$0) = sq_1:b.EXPR$0)","edgeType":"PREDICATE"},{"sources":[],"targets":[0,1],"expression":"(1 = 1)","edgeType":"PREDICATE"},{"sources":[4],"targets":[0,1],"expression":"UDFToDouble((UDFToInteger(sq_1:b.ctinyint) + 300)) is not null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"$hdt$_0.key"},{"id":1,"vertexType":"COLUMN","vertexId":"$hdt$_0.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"}]} 311 val_311 -Warning: Shuffle Join JOIN[18][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[12][tables = [src1, ]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select key, value from src1 where key not in (select key+18 from src1) order by key PREHOOK: type: QUERY PREHOOK: Input: default@src1 #### A masked pattern was here #### -{"version":"1.0","engine":"mr","hash":"9b488fe1d7cf018aad3825173808cd36","queryText":"select key, value from src1\nwhere key not in (select key+18 from src1) order by key","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[],"targets":[0,1],"expression":"(1 = 1)","edgeType":"PREDICATE"},{"sources":[2],"targets":[0,1],"expression":"(UDFToDouble(src1.key) + UDFToDouble(18)) is null","edgeType":"PREDICATE"},{"sources":[4],"targets":[0,1],"expression":"(count(*) = 0)","edgeType":"PREDICATE"},{"sources":[],"targets":[0,1],"expression":"true","edgeType":"PREDICATE"},{"sources":[2],"targets":[0,1],"expression":"(UDFToDouble(src1.key) = (UDFToDouble(src1.key) + UDFToDouble(18)))","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"key"},{"id":1,"vertexType":"COLUMN","vertexId":"value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"},{"id":4,"vertexType":"TABLE","vertexId":"default.src1"}]} +{"version":"1.0","engine":"mr","hash":"9b488fe1d7cf018aad3825173808cd36","queryText":"select key, value from src1\nwhere key not in (select key+18 from src1) order by key","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[],"targets":[0,1],"expression":"(1 = 1)","edgeType":"PREDICATE"},{"sources":[2],"targets":[0,1],"expression":"(UDFToDouble(sq_1_notin_nullcheck:sq_1:src1.key) + UDFToDouble(18)) is null","edgeType":"PREDICATE"},{"sources":[4],"targets":[0,1],"expression":"(count(*) = 0)","edgeType":"PREDICATE"},{"sources":[2],"targets":[0,1],"expression":"(UDFToDouble(src1.key) = (UDFToDouble(sq_1:src1.key) + UDFToDouble(18)))","edgeType":"PREDICATE"},{"sources":[2],"targets":[0,1],"expression":"(UDFToDouble(sq_1:src1.key) + UDFToDouble(18)) is null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"$hdt$_0.key"},{"id":1,"vertexType":"COLUMN","vertexId":"$hdt$_0.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"},{"id":4,"vertexType":"TABLE","vertexId":"default.src1"}]} PREHOOK: query: select * from src1 a where not exists (select cint from alltypesorc b @@ -196,7 +196,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@alltypesorc PREHOOK: Input: default@src1 #### A masked pattern was here #### -{"version":"1.0","engine":"mr","hash":"53191056e05af9080a30de853e8cea9c","queryText":"select * from src1 a\nwhere not exists\n (select cint from alltypesorc b\n where a.key = b.ctinyint + 300)\nand key > 300","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2],"targets":[0,1],"expression":"(UDFToDouble(a.key) > UDFToDouble(300))","edgeType":"PREDICATE"},{"sources":[2,4],"targets":[0,1],"expression":"(UDFToDouble(a.key) = UDFToDouble((UDFToInteger(b.ctinyint) + 300)))","edgeType":"PREDICATE"},{"sources":[],"targets":[0,1],"expression":"(1 = 1)","edgeType":"PREDICATE"},{"sources":[4],"targets":[0,1],"expression":"(UDFToInteger(b.ctinyint) + 300) is null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"a.key"},{"id":1,"vertexType":"COLUMN","vertexId":"a.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"}]} +{"version":"1.0","engine":"mr","hash":"53191056e05af9080a30de853e8cea9c","queryText":"select * from src1 a\nwhere not exists\n (select cint from alltypesorc b\n where a.key = b.ctinyint + 300)\nand key > 300","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2],"targets":[0,1],"expression":"(UDFToDouble(a.key) > UDFToDouble(300))","edgeType":"PREDICATE"},{"sources":[2,4],"targets":[0,1],"expression":"(UDFToDouble(a.key) = UDFToDouble((UDFToInteger(sq_1:b.ctinyint) + 300)))","edgeType":"PREDICATE"},{"sources":[],"targets":[0,1],"expression":"(1 = 1)","edgeType":"PREDICATE"},{"sources":[4],"targets":[0,1],"expression":"(UDFToInteger(sq_1:b.ctinyint) + 300) is null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"$hdt$_0.key"},{"id":1,"vertexType":"COLUMN","vertexId":"$hdt$_0.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"}]} 369 401 val_401 406 val_406 @@ -205,7 +205,7 @@ select x, y from t where y > 'v' order by x, y limit 5 PREHOOK: type: QUERY PREHOOK: Input: default@src1 #### A masked pattern was here #### -{"version":"1.0","engine":"mr","hash":"d40d80b93db06c12df9a6ccdc108a9d1","queryText":"with t as (select key x, value y from src1 where key > '2')\nselect x, y from t where y > 'v' order by x, y limit 5","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2],"targets":[0,1],"expression":"(src1.key > '2')","edgeType":"PREDICATE"},{"sources":[3],"targets":[0,1],"expression":"(src1.value > 'v')","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"x"},{"id":1,"vertexType":"COLUMN","vertexId":"y"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"}]} +{"version":"1.0","engine":"mr","hash":"d40d80b93db06c12df9a6ccdc108a9d1","queryText":"with t as (select key x, value y from src1 where key > '2')\nselect x, y from t where y > 'v' order by x, y limit 5","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2],"targets":[0,1],"expression":"(t:src1.key > '2')","edgeType":"PREDICATE"},{"sources":[3],"targets":[0,1],"expression":"(t:src1.value > 'v')","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"t.key"},{"id":1,"vertexType":"COLUMN","vertexId":"t.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"}]} 213 val_213 238 val_238 255 val_255 @@ -216,7 +216,7 @@ select x, y where y > 'v' order by x, y limit 5 PREHOOK: type: QUERY PREHOOK: Input: default@src1 #### A masked pattern was here #### -{"version":"1.0","engine":"mr","hash":"9180b71a610dbcf5e636a3c03e48ca3b","queryText":"from (select key x, value y from src1 where key > '2') t\nselect x, y where y > 'v' order by x, y limit 5","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2],"targets":[0,1],"expression":"(src1.key > '2')","edgeType":"PREDICATE"},{"sources":[3],"targets":[0,1],"expression":"(src1.value > 'v')","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"x"},{"id":1,"vertexType":"COLUMN","vertexId":"y"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"}]} +{"version":"1.0","engine":"mr","hash":"9180b71a610dbcf5e636a3c03e48ca3b","queryText":"from (select key x, value y from src1 where key > '2') t\nselect x, y where y > 'v' order by x, y limit 5","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2],"targets":[0,1],"expression":"(t:src1.key > '2')","edgeType":"PREDICATE"},{"sources":[3],"targets":[0,1],"expression":"(t:src1.value > 'v')","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"t.key"},{"id":1,"vertexType":"COLUMN","vertexId":"t.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"}]} 213 val_213 238 val_238 255 val_255 @@ -236,7 +236,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@alltypesorc PREHOOK: Input: default@dest_v1 #### A masked pattern was here #### -{"version":"1.0","engine":"mr","hash":"75e07b246069a5541af4a3983500b439","queryText":"select * from dest_v1 order by ctinyint, cint limit 2","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2],"targets":[0,1],"expression":"alltypesorc.ctinyint is not null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"dest_v1.ctinyint"},{"id":1,"vertexType":"COLUMN","vertexId":"dest_v1.cint"},{"id":2,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":3,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"}]} +{"version":"1.0","engine":"mr","hash":"75e07b246069a5541af4a3983500b439","queryText":"select * from dest_v1 order by ctinyint, cint limit 2","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2],"targets":[0,1],"expression":"dest_v1:alltypesorc.ctinyint is not null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"dest_v1.ctinyint"},{"id":1,"vertexType":"COLUMN","vertexId":"dest_v1.cint"},{"id":2,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":3,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"}]} -64 NULL -64 NULL PREHOOK: query: alter view dest_v1 as select ctinyint from alltypesorc @@ -251,7 +251,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@alltypesorc PREHOOK: Input: default@dest_v1 #### A masked pattern was here #### -{"version":"1.0","engine":"mr","hash":"b0192d4da86f4bef38fe7ab1fc607906","queryText":"select t.ctinyint from (select * from dest_v1 where ctinyint is not null) t\nwhere ctinyint > 10 order by ctinyint limit 2","edges":[{"sources":[1],"targets":[0],"edgeType":"PROJECTION"},{"sources":[1],"targets":[0],"expression":"alltypesorc.ctinyint is not null","edgeType":"PREDICATE"},{"sources":[1],"targets":[0],"expression":"(alltypesorc.ctinyint > 10)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"t.ctinyint"},{"id":1,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"}]} +{"version":"1.0","engine":"mr","hash":"b0192d4da86f4bef38fe7ab1fc607906","queryText":"select t.ctinyint from (select * from dest_v1 where ctinyint is not null) t\nwhere ctinyint > 10 order by ctinyint limit 2","edges":[{"sources":[1],"targets":[0],"edgeType":"PROJECTION"},{"sources":[1],"targets":[0],"expression":"t:dest_v1:alltypesorc.ctinyint is not null","edgeType":"PREDICATE"},{"sources":[1],"targets":[0],"expression":"(t:dest_v1:alltypesorc.ctinyint > 10)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"t.ctinyint"},{"id":1,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"}]} 11 11 PREHOOK: query: drop view if exists dest_v2 @@ -317,6 +317,6 @@ PREHOOK: type: QUERY PREHOOK: Input: default@alltypesorc PREHOOK: Input: default@dest_v3 #### A masked pattern was here #### -{"version":"1.0","engine":"mr","hash":"40bccc0722002f798d0548b59e369e83","queryText":"select * from dest_v3 limit 2","edges":[{"sources":[3,4,5,6,7],"targets":[0],"expression":"(tok_function sum (. (tok_table_or_col $hdt$_0) $f0) (tok_windowspec (tok_partitioningspec (tok_distributeby (. (tok_table_or_col $hdt$_0) $f1)) (tok_orderby (tok_tabsortcolnameasc (. (tok_table_or_col $hdt$_0) $f1)))) (tok_windowvalues (preceding 2147483647) current)))","edgeType":"PROJECTION"},{"sources":[6],"targets":[1],"expression":"count(default.alltypesorc.cstring1)","edgeType":"PROJECTION"},{"sources":[5],"targets":[2],"edgeType":"PROJECTION"},{"sources":[8],"targets":[0,1,2],"expression":"(a.cboolean2 = true)","edgeType":"PREDICATE"},{"sources":[7],"targets":[0,1,2],"expression":"(a.cint = a.cint)","edgeType":"PREDICATE"},{"sources":[9],"targets":[0,1,2],"expression":"(a.cfloat > 0.0)","edgeType":"PREDICATE"},{"sources":[7],"targets":[0,1,2],"expression":"(count(default.alltypesorc.cint) > 10)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"dest_v3.a"},{"id":1,"vertexType":"COLUMN","vertexId":"dest_v3.x"},{"id":2,"vertexType":"COLUMN","vertexId":"dest_v3.cboolean1"},{"id":3,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":4,"vertexType":"COLUMN","vertexId":"default.alltypesorc.csmallint"},{"id":5,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cboolean1"},{"id":6,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cstring1"},{"id":7,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"},{"id":8,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cboolean2"},{"id":9,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cfloat"}]} +{"version":"1.0","engine":"mr","hash":"40bccc0722002f798d0548b59e369e83","queryText":"select * from dest_v3 limit 2","edges":[],"vertices":[]} 38 216 false 38 229 true diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_1.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_1.q.out index 067ac5d..2de08e5 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_1.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_1.q.out @@ -80,7 +80,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -491,7 +491,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '484' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_11.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_11.q.java1.7.out index 8cc1370..8e7d77c 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_11.q.java1.7.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_11.q.java1.7.out @@ -83,7 +83,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -365,7 +365,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 'val_466' (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_12.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_12.q.java1.7.out index b0735a3..73b1778 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_12.q.java1.7.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_12.q.java1.7.out @@ -378,7 +378,7 @@ STAGE PLANS: Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: col1 (type: string), '466' (type: string), col3 (type: string), 'val_466' (type: string), col5 (type: string), '2008-04-08' (type: string), '11' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: col1, col2, col3, col4, col5, ds, hr Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE ListSink @@ -504,7 +504,7 @@ STAGE PLANS: Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: col1 (type: string), '382' (type: string), col3 (type: string), 'val_382' (type: string), col5 (type: string), '2008-04-08' (type: string), '11' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: col1, col2, col3, col4, col5, ds, hr Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_13.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_13.q.java1.7.out index 6761092..7dd9a0b 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_13.q.java1.7.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_13.q.java1.7.out @@ -378,7 +378,7 @@ STAGE PLANS: Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: col1 (type: string), '466' (type: string), col3 (type: string), 'val_466' (type: string), col5 (type: string), '2008-04-08' (type: string), '2013-01-23+18:00:99' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: col1, col2, col3, col4, col5, ds, hr Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_14.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_14.q.out index 1519b96..ebf47b9 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_14.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_14.q.out @@ -60,7 +60,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -292,7 +292,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '484' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -305,7 +305,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1 + columns key,value columns.types string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_2.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_2.q.java1.7.out index 59bb498..1487037 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_2.q.java1.7.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_2.q.java1.7.out @@ -104,7 +104,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -464,7 +464,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out index fad6cb9..37fe876 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out @@ -72,7 +72,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -433,7 +433,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '484' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_4.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_4.q.java1.7.out index 23d6896..e8dacd7 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_4.q.java1.7.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_4.q.java1.7.out @@ -112,7 +112,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -406,7 +406,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -873,7 +873,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_5.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_5.q.java1.7.out index ce8bb4a..2c379cc 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_5.q.java1.7.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_5.q.java1.7.out @@ -84,7 +84,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -550,7 +550,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '103' (type: string), 'val_103' (type: string), '2008-04-08' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.7.out index c3ede05..56fcb2e 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.7.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.7.out @@ -168,7 +168,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, _o__c2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -519,7 +519,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, _o__c2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1075,7 +1075,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_7.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_7.q.out index 7bf4a21..bdd70e6 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_7.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_7.q.out @@ -114,7 +114,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, _o__c2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -465,7 +465,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, _o__c2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1021,7 +1021,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_8.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_8.q.java1.7.out index fc22118..911def4 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_8.q.java1.7.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_8.q.java1.7.out @@ -170,7 +170,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, _o__c2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -668,7 +668,7 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 34 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 4 Data size: 34 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_9.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_9.q.java1.7.out index 8975ec0..2735bad 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_9.q.java1.7.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_9.q.java1.7.out @@ -112,7 +112,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -406,7 +406,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -873,7 +873,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_1.q.out b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_1.q.out index 7c4b70c..39a8521 100644 --- a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_1.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_1.q.out @@ -216,7 +216,7 @@ STAGE PLANS: Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '484' (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE ListSink @@ -344,7 +344,7 @@ STAGE PLANS: Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '238' (type: string), 'val_238' (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE ListSink @@ -465,7 +465,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE ListSink @@ -587,7 +587,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '495' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out index 7f32108..a52bd82 100644 --- a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out @@ -214,7 +214,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 'val_484' (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE ListSink @@ -334,7 +334,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '406' (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE ListSink @@ -475,7 +475,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out index 753729f..3f18a5a 100644 --- a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out @@ -328,7 +328,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '145' (type: string), value (type: string), '1' (type: string), '1' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE ListSink @@ -451,35 +451,39 @@ STAGE PLANS: name: default.fact_daily name: default.fact_daily Truncated Path -> Alias: - /fact_daily/ds=1/hr=1 [$hdt$_0:fact_daily] + /fact_daily/ds=1/hr=1 [fact_daily] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns $f0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -605,7 +609,7 @@ STAGE PLANS: Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '484' (type: string), 'val_484' (type: string), '1' (type: string), '2' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE ListSink @@ -727,7 +731,7 @@ STAGE PLANS: Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '327' (type: string), 'val_327' (type: string), '1' (type: string), '3' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_1.q.out b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_1.q.out index bec4f6a..584031d 100644 --- a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_1.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_1.q.out @@ -269,7 +269,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 484 (type: int) - outputColumnNames: _col0 + outputColumnNames: x Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE ListSink @@ -384,7 +384,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 495 (type: int) - outputColumnNames: _col0 + outputColumnNames: x Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE ListSink @@ -495,7 +495,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 1 (type: int) - outputColumnNames: _col0 + outputColumnNames: x Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out index 646f8b8..b9fd146 100644 --- a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out @@ -277,7 +277,7 @@ STAGE PLANS: name: default.fact_daily Processor Tree: TableScan - alias: fact_daily + alias: subq:fact_daily Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator @@ -286,7 +286,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 484 (type: int) - outputColumnNames: _col0 + outputColumnNames: x Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE ListSink @@ -412,7 +412,7 @@ STAGE PLANS: name: default.fact_daily Processor Tree: TableScan - alias: fact_daily + alias: subq:fact_daily Statistics: Num rows: 1 Data size: 24 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator @@ -421,7 +421,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 484 (type: int), y (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: x1, y1 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE ListSink @@ -497,12 +497,12 @@ STAGE PLANS: predicate: (x = 484) (type: boolean) Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: y (type: string) - outputColumnNames: _col0 + expressions: y (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -564,36 +564,40 @@ STAGE PLANS: name: default.fact_daily name: default.fact_daily Truncated Path -> Alias: - /fact_tz/ds=1/x=484 [$hdt$_0:fact_daily] + /fact_tz/ds=1/x=484 [fact_daily] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1 - columns.types string:bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns $f0,$f1 + columns.types string:bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -681,7 +685,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: fact_daily + alias: subq:fact_daily Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator @@ -689,12 +693,12 @@ STAGE PLANS: predicate: (x = 484) (type: boolean) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 484 (type: int) - outputColumnNames: _col0 + expressions: 484 (type: int), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int) + aggregations: count($f1) + keys: $f0 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -756,36 +760,40 @@ STAGE PLANS: name: default.fact_daily name: default.fact_daily Truncated Path -> Alias: - /fact_tz/ds=1/x=484 [$hdt$_0:$hdt$_0:fact_daily] + /fact_tz/ds=1/x=484 [subq:fact_daily] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: $f0 (type: int), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1 - columns.types int:bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns $f0,$f1 + columns.types int:bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_3.q.out b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_3.q.out index bef079b..407d1f0 100644 --- a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_3.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_3.q.out @@ -297,7 +297,7 @@ STAGE PLANS: Statistics: Num rows: 29 Data size: 117 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: x (type: int) - outputColumnNames: _col0 + outputColumnNames: x Statistics: Num rows: 29 Data size: 117 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/literal_double.q.out b/ql/src/test/results/clientpositive/literal_double.q.out index 5d46d2d..18c7303 100644 --- a/ql/src/test/results/clientpositive/literal_double.q.out +++ b/ql/src/test/results/clientpositive/literal_double.q.out @@ -15,7 +15,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 3.14 (type: double), -3.14 (type: double), 3.14E8 (type: double), 3.14E-8 (type: double), -3.14E8 (type: double), -3.14E-8 (type: double), 3.14E8 (type: double), 3.14E8 (type: double), 3.14E-8 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8 Statistics: Num rows: 500 Data size: 36000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 diff --git a/ql/src/test/results/clientpositive/literal_ints.q.out b/ql/src/test/results/clientpositive/literal_ints.q.out index 9a56ebd..7eb209e 100644 --- a/ql/src/test/results/clientpositive/literal_ints.q.out +++ b/ql/src/test/results/clientpositive/literal_ints.q.out @@ -15,7 +15,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 100 (type: int), 100 (type: tinyint), 100 (type: smallint), 100 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3 Statistics: Num rows: 500 Data size: 10000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 diff --git a/ql/src/test/results/clientpositive/literal_string.q.out b/ql/src/test/results/clientpositive/literal_string.q.out index b2f5e12..4d9ca74 100644 --- a/ql/src/test/results/clientpositive/literal_string.q.out +++ b/ql/src/test/results/clientpositive/literal_string.q.out @@ -25,7 +25,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'facebook' (type: string), 'facebook' (type: string), 'facebook' (type: string), 'facebook' (type: string), 'facebook' (type: string), 'facebook' (type: string), 'facebook' (type: string), 'facebook' (type: string), 'facebook' (type: string), 'facebook' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9 Statistics: Num rows: 500 Data size: 460000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 diff --git a/ql/src/test/results/clientpositive/load_dyn_part10.q.out b/ql/src/test/results/clientpositive/load_dyn_part10.q.out index ca388b9..e5212ae 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part10.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part10.q.out @@ -60,7 +60,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/load_dyn_part13.q.out b/ql/src/test/results/clientpositive/load_dyn_part13.q.out index 9e0ac6f..5af8703 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part13.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part13.q.out @@ -66,45 +66,53 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1:s-subquery1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 20.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '22' (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, _o__c2 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), _o__c2 (type: char(2)) + outputColumnNames: key, value, _o__c2 Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part13 + File Output Operator + compressed: false + Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part13 TableScan - alias: src + alias: null-subquery2:s-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 20.0) and (UDFToDouble(key) < 40.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '33' (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, _o__c2 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), _o__c2 (type: char(2)) + outputColumnNames: key, value, _o__c2 Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part13 + File Output Operator + compressed: false + Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part13 Stage: Stage-0 Move Operator @@ -147,10 +155,10 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@nzhang_part13@ds=2010-03-03/hr=22 POSTHOOK: Output: default@nzhang_part13@ds=2010-03-03/hr=33 -POSTHOOK: Lineage: nzhang_part13 PARTITION(ds=2010-03-03,hr=22).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: nzhang_part13 PARTITION(ds=2010-03-03,hr=22).value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: nzhang_part13 PARTITION(ds=2010-03-03,hr=33).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: nzhang_part13 PARTITION(ds=2010-03-03,hr=33).value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: nzhang_part13 PARTITION(ds=2010-03-03,hr=22).key EXPRESSION [(src)null-subquery1:s-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:s-subquery2:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: nzhang_part13 PARTITION(ds=2010-03-03,hr=22).value EXPRESSION [(src)null-subquery1:s-subquery1:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery2:s-subquery2:src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: nzhang_part13 PARTITION(ds=2010-03-03,hr=33).key EXPRESSION [(src)null-subquery1:s-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:s-subquery2:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: nzhang_part13 PARTITION(ds=2010-03-03,hr=33).value EXPRESSION [(src)null-subquery1:s-subquery1:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery2:s-subquery2:src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: show partitions nzhang_part13 PREHOOK: type: SHOWPARTITIONS PREHOOK: Input: default@nzhang_part13 diff --git a/ql/src/test/results/clientpositive/load_dyn_part14.q.out b/ql/src/test/results/clientpositive/load_dyn_part14.q.out index 57a1a93..6b10f5a 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part14.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part14.q.out @@ -55,88 +55,103 @@ select key, value from ( POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-9, Stage-10 - Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 - Stage-5 - Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 - Stage-3 depends on stages: Stage-0 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 Stage-4 - Stage-6 - Stage-7 depends on stages: Stage-6 - Stage-9 is a root stage - Stage-10 is a root stage + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 + Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1-subquery1:t-subquery1-subquery1:a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 'k1' (type: string), null (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 43000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 2 Statistics: Num rows: 2 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 2 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Limit - Number of rows: 2 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator - expressions: 'k1' (type: string), null (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Union - Statistics: Num rows: 6 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part14 + Union + Statistics: Num rows: 6 Data size: 1644 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: char(2)), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part14 TableScan - Union - Statistics: Num rows: 6 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part14 + alias: null-subquery1-subquery2:t-subquery1-subquery2:b:src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 'k2' (type: string), '' (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 85000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 2 + Statistics: Num rows: 2 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: UDFToString(key) (type: string), UDFToString(value) (type: string) + outputColumnNames: key, value + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: COMPLETE + Union + Statistics: Num rows: 6 Data size: 1644 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: char(2)), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part14 TableScan - Union - Statistics: Num rows: 6 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part14 + alias: null-subquery2:t-subquery2:c:src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 'k3' (type: string), ' ' (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 85500 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 2 + Statistics: Num rows: 2 Data size: 342 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: UDFToString(key) (type: string), UDFToString(value) (type: string) + outputColumnNames: key, value + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: COMPLETE + Union + Statistics: Num rows: 6 Data size: 1644 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: char(2)), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part14 - Stage: Stage-8 + Stage: Stage-7 Conditional Operator - Stage: Stage-5 + Stage: Stage-4 Move Operator files: hdfs directory: true @@ -154,10 +169,10 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part14 - Stage: Stage-3 + Stage: Stage-2 Stats-Aggr Operator - Stage: Stage-4 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan @@ -169,7 +184,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part14 - Stage: Stage-6 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan @@ -181,70 +196,12 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part14 - Stage: Stage-7 + Stage: Stage-6 Move Operator files: hdfs directory: true #### A masked pattern was here #### - Stage: Stage-9 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 500 Data size: 85000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 2 - Statistics: Num rows: 2 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 2 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Limit - Number of rows: 2 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator - expressions: 'k2' (type: string), '' (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-10 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 500 Data size: 85500 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 2 - Statistics: Num rows: 2 Data size: 342 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 2 Data size: 342 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Limit - Number of rows: 2 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator - expressions: 'k3' (type: string), ' ' (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - PREHOOK: query: insert overwrite table nzhang_part14 partition(value) select key, value from ( select * from (select 'k1' as key, cast(null as string) as value from src limit 2)a diff --git a/ql/src/test/results/clientpositive/load_dyn_part2.q.out b/ql/src/test/results/clientpositive/load_dyn_part2.q.out index 0c5fe6b..870ed0c 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part2.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part2.q.out @@ -52,13 +52,13 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, hr Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + value expressions: key (type: string), value (type: string), hr (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string) diff --git a/ql/src/test/results/clientpositive/load_dyn_part3.q.out b/ql/src/test/results/clientpositive/load_dyn_part3.q.out index 3242c3d..3b268df 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part3.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part3.q.out @@ -58,7 +58,7 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/load_dyn_part4.q.out b/ql/src/test/results/clientpositive/load_dyn_part4.q.out index d24875f..660d093 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part4.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part4.q.out @@ -68,7 +68,7 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/load_dyn_part5.q.out b/ql/src/test/results/clientpositive/load_dyn_part5.q.out index e4bc742..55ff3a5 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part5.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part5.q.out @@ -41,7 +41,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/load_dyn_part9.q.out b/ql/src/test/results/clientpositive/load_dyn_part9.q.out index 300f41e..e2043ad 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part9.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part9.q.out @@ -60,7 +60,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/louter_join_ppr.q.out b/ql/src/test/results/clientpositive/louter_join_ppr.q.out index 1b2b8e3..887626d 100644 --- a/ql/src/test/results/clientpositive/louter_join_ppr.q.out +++ b/ql/src/test/results/clientpositive/louter_join_ppr.q.out @@ -122,15 +122,15 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false TableScan alias: b @@ -142,15 +142,15 @@ STAGE PLANS: Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -292,44 +292,48 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:$hdt$_1:b] + /src [a] + /srcpart/ds=2008-04-08/hr=11 [b] + /srcpart/ds=2008-04-08/hr=12 [b] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean) + predicate: ((UDFToDouble(key0) > 15.0) and (UDFToDouble(key0) < 25.0)) (type: boolean) Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns key,value,key0,value0 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -495,15 +499,15 @@ STAGE PLANS: Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col1 (type: string), _col2 (type: string) + value expressions: value (type: string), ds (type: string) auto parallelism: false TableScan alias: b @@ -515,15 +519,15 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -757,11 +761,11 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:a] - /srcpart/ds=2008-04-09/hr=11 [$hdt$_0:a] - /srcpart/ds=2008-04-09/hr=12 [$hdt$_0:a] + /src [b] + /srcpart/ds=2008-04-08/hr=11 [a] + /srcpart/ds=2008-04-08/hr=12 [a] + /srcpart/ds=2008-04-09/hr=11 [a] + /srcpart/ds=2008-04-09/hr=12 [a] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -770,20 +774,20 @@ STAGE PLANS: filter mappings: 0 [1, 1] filter predicates: - 0 {(VALUE._col1 = '2008-04-08')} + 0 {(VALUE.ds = '2008-04-08')} 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3, _col4 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 244 Data size: 2593 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((UDFToDouble(_col3) > 15.0) and (UDFToDouble(_col3) < 25.0)) (type: boolean) + predicate: ((UDFToDouble(key0) > 15.0) and (UDFToDouble(key0) < 25.0)) (type: boolean) Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -796,7 +800,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2,_col3 + columns key,value,key0,value0 columns.types string:string:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -971,19 +975,19 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + predicate: ((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) (type: boolean) + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false TableScan alias: a @@ -991,19 +995,19 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: (((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 15.0)) and (UDFToDouble(key) < 25.0)) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 15.0)) and (UDFToDouble(key) < 25.0)) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -1145,35 +1149,35 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [$hdt$_1:$hdt$_1:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:$hdt$_0:b] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:$hdt$_0:b] + /src [a] + /srcpart/ds=2008-04-08/hr=11 [b] + /srcpart/ds=2008-04-08/hr=12 [b] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + expressions: key0 (type: string), value0 (type: string), key (type: string), value (type: string) + outputColumnNames: key, value, key1, value1 + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2,_col3 + columns key,value,key1,value1 columns.types string:string:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -1348,15 +1352,15 @@ STAGE PLANS: Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false TableScan alias: b @@ -1368,15 +1372,15 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -1518,26 +1522,26 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:a] + /src [b] + /srcpart/ds=2008-04-08/hr=11 [a] + /srcpart/ds=2008-04-08/hr=12 [a] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3, _col4 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((UDFToDouble(_col3) > 15.0) and (UDFToDouble(_col3) < 25.0)) (type: boolean) + predicate: ((UDFToDouble(key0) > 15.0) and (UDFToDouble(key0) < 25.0)) (type: boolean) Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1550,7 +1554,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2,_col3 + columns key,value,key0,value0 columns.types string:string:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true diff --git a/ql/src/test/results/clientpositive/macro.q.out b/ql/src/test/results/clientpositive/macro.q.out index 76ea250..59d06ee 100644 --- a/ql/src/test/results/clientpositive/macro.q.out +++ b/ql/src/test/results/clientpositive/macro.q.out @@ -30,7 +30,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 0.8807970779778823 (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 500 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 @@ -75,7 +75,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: 0.8807970779778823 (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 500 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 @@ -120,7 +120,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 2 (type: int) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 @@ -166,7 +166,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: 2 (type: int) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 @@ -238,7 +238,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 10 (type: int) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 @@ -284,7 +284,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: 10 (type: int) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 diff --git a/ql/src/test/results/clientpositive/mapjoin_distinct.q.out b/ql/src/test/results/clientpositive/mapjoin_distinct.q.out index 4df25ca..165f659 100644 --- a/ql/src/test/results/clientpositive/mapjoin_distinct.q.out +++ b/ql/src/test/results/clientpositive/mapjoin_distinct.q.out @@ -53,16 +53,20 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col1 (type: string) - mode: hash - outputColumnNames: _col0 + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: rand() (type: double) + Group By Operator + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: rand() (type: double) + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -93,13 +97,17 @@ STAGE PLANS: mode: final outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -189,16 +197,20 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col1 (type: string) - mode: hash - outputColumnNames: _col0 + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -207,13 +219,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -304,11 +320,15 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: rand() (type: double) + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: rand() (type: double) + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -339,13 +359,17 @@ STAGE PLANS: mode: final outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -435,11 +459,15 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -448,13 +476,17 @@ STAGE PLANS: mode: complete outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/mapjoin_hook.q.out b/ql/src/test/results/clientpositive/mapjoin_hook.q.out index 8a6743c..6d7fb85 100644 --- a/ql/src/test/results/clientpositive/mapjoin_hook.q.out +++ b/ql/src/test/results/clientpositive/mapjoin_hook.q.out @@ -56,11 +56,11 @@ ATTEMPT: Execute BackupTask: org.apache.hadoop.hive.ql.exec.mr.MapRedTask FAILED: Execution Error, return code 3 from org.apache.hadoop.hive.ql.exec.mr.MapredLocalTask ATTEMPT: Execute BackupTask: org.apache.hadoop.hive.ql.exec.mr.MapRedTask [MapJoinCounter PostHook] COMMON_JOIN: 0 HINTED_MAPJOIN: 0 HINTED_MAPJOIN_LOCAL: 0 CONVERTED_MAPJOIN: 0 CONVERTED_MAPJOIN_LOCAL: 2 BACKUP_COMMON_JOIN: 2 -RUN: Stage-11:CONDITIONAL -RUN: Stage-14:MAPREDLOCAL -RUN: Stage-1:MAPRED -RUN: Stage-8:CONDITIONAL +RUN: Stage-10:CONDITIONAL +RUN: Stage-13:MAPREDLOCAL +RUN: Stage-3:MAPRED +RUN: Stage-7:CONDITIONAL RUN: Stage-12:MAPREDLOCAL -RUN: Stage-2:MAPRED +RUN: Stage-1:MAPRED RUN: Stage-0:MOVE -RUN: Stage-3:STATS +RUN: Stage-2:STATS diff --git a/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out b/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out index 9775f30..35c2831 100644 --- a/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out @@ -56,22 +56,22 @@ TOK_QUERY STAGE DEPENDENCIES: - Stage-7 is a root stage - Stage-5 depends on stages: Stage-7 - Stage-0 depends on stages: Stage-5 + Stage-6 is a root stage + Stage-4 depends on stages: Stage-6 + Stage-0 depends on stages: Stage-4 STAGE PLANS: - Stage: Stage-7 + Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:src + src Fetch Operator limit: -1 - $hdt$_2:src1 + src1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:src + src TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -82,14 +82,14 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - Position of Big Table: 0 - $hdt$_2:src1 + 0 value (type: string) + 1 value (type: string) + Position of Big Table: 1 + src1 TableScan alias: src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -100,15 +100,15 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Position of Big Table: 0 + 0 key (type: string) + 1 key (type: string) + Position of Big Table: 1 - Stage: Stage-5 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan @@ -117,51 +117,59 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: (key is not null and value is not null) (type: boolean) + predicate: (value is not null and key is not null) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Position of Big Table: 0 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key + Position of Big Table: 1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Position of Big Table: 0 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 + Position of Big Table: 1 + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key0 (type: string) + outputColumnNames: key + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns key + columns.types string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Local Work: Map Reduce Local Work Path -> Alias: @@ -440,10 +448,10 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:srcpart] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:srcpart] - /srcpart/ds=2008-04-09/hr=11 [$hdt$_1:srcpart] - /srcpart/ds=2008-04-09/hr=12 [$hdt$_1:srcpart] + /srcpart/ds=2008-04-08/hr=11 [srcpart] + /srcpart/ds=2008-04-08/hr=12 [srcpart] + /srcpart/ds=2008-04-09/hr=11 [srcpart] + /srcpart/ds=2008-04-09/hr=12 [srcpart] Stage: Stage-0 Fetch Operator @@ -458,22 +466,22 @@ POSTHOOK: query: explain select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) where srcpart.value > 'val_450' POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-7 is a root stage - Stage-5 depends on stages: Stage-7 - Stage-0 depends on stages: Stage-5 + Stage-6 is a root stage + Stage-4 depends on stages: Stage-6 + Stage-0 depends on stages: Stage-4 STAGE PLANS: - Stage: Stage-7 + Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:src + src Fetch Operator limit: -1 - $hdt$_2:src1 + src1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:src + src TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -482,13 +490,13 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - $hdt$_2:src1 + 0 value (type: string) + 1 value (type: string) + src1 TableScan alias: src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -497,49 +505,56 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) - Stage: Stage-5 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((value > 'val_450') and key is not null) and value is not null) (type: boolean) - Statistics: Num rows: 167 Data size: 1774 Basic stats: COMPLETE Column stats: NONE + predicate: ((value is not null and key is not null) and (value > 'val_450')) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 167 Data size: 1774 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 183 Data size: 1951 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 201 Data size: 2146 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 201 Data size: 2146 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0 + Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key0 (type: string) + outputColumnNames: key + Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -556,21 +571,21 @@ POSTHOOK: query: explain select count(*) from srcpart join src on (srcpart.value=src.value) join src src1 on (srcpart.key=src1.key) group by ds POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-9 is a root stage - Stage-7 depends on stages: Stage-9 - Stage-8 depends on stages: Stage-7 - Stage-3 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-3 + Stage-8 is a root stage + Stage-6 depends on stages: Stage-8 + Stage-7 depends on stages: Stage-6 + Stage-2 depends on stages: Stage-7 + Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-9 + Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:src + src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:src + src TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -579,14 +594,14 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col1 (type: string) - 1 _col0 (type: string) + 0 value (type: string) + 1 value (type: string) - Stage: Stage-7 + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan @@ -597,49 +612,52 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key, ds Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work - Stage: Stage-8 + Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_2:src + src1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_2:src + src1 TableScan - alias: src + alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) - Stage: Stage-3 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan @@ -647,25 +665,25 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col2 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + outputColumnNames: ds + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + expressions: ds (type: string) + outputColumnNames: $f0 + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work @@ -674,15 +692,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE + expressions: $f1 (type: bigint) + outputColumnNames: _o__c0 + Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/mapjoin_subquery.q.out b/ql/src/test/results/clientpositive/mapjoin_subquery.q.out index 1f7a5f4..f581a19 100644 --- a/ql/src/test/results/clientpositive/mapjoin_subquery.q.out +++ b/ql/src/test/results/clientpositive/mapjoin_subquery.q.out @@ -19,96 +19,88 @@ FROM JOIN srcpart z ON (subq.key1 = z.key and z.ds='2008-04-08' and z.hr=11) POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-6 is a root stage - Stage-4 depends on stages: Stage-6 + Stage-5 is a root stage + Stage-4 depends on stages: Stage-5 Stage-0 depends on stages: Stage-4 STAGE PLANS: - Stage: Stage-6 + Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:z + subq:x Fetch Operator limit: -1 - $hdt$_1:$hdt$_2:x + subq:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:z + subq:x TableScan - alias: z - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: subq:x + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - $hdt$_1:$hdt$_2:x + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + subq:y TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: subq:y + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: y + alias: z Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 + Inner Join 1 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: key0, value1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col4 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col4 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + expressions: key0 (type: string), value1 (type: string) + outputColumnNames: key1, value + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -262,96 +254,88 @@ FROM JOIN srcpart z ON (subq.key1 = z.key and z.ds='2008-04-08' and z.hr=11) POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-6 is a root stage - Stage-4 depends on stages: Stage-6 + Stage-5 is a root stage + Stage-4 depends on stages: Stage-5 Stage-0 depends on stages: Stage-4 STAGE PLANS: - Stage: Stage-6 + Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:z + subq:x Fetch Operator limit: -1 - $hdt$_1:$hdt$_2:x + subq:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:z + subq:x TableScan - alias: z - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: subq:x + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - $hdt$_1:$hdt$_2:x + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + subq:y TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: subq:y + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: y + alias: z Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 + Inner Join 1 to 2 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: key0, value1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col4 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col4 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + expressions: key0 (type: string), value1 (type: string) + outputColumnNames: key1, value + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/mapjoin_subquery2.q.out b/ql/src/test/results/clientpositive/mapjoin_subquery2.q.out index 7e1e66b..fc9c45d 100644 --- a/ql/src/test/results/clientpositive/mapjoin_subquery2.q.out +++ b/ql/src/test/results/clientpositive/mapjoin_subquery2.q.out @@ -150,13 +150,17 @@ STAGE PLANS: 1 id (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: int), _col5 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/merge1.q.out b/ql/src/test/results/clientpositive/merge1.q.out index 94089fc..31b1cc1 100644 --- a/ql/src/test/results/clientpositive/merge1.q.out +++ b/ql/src/test/results/clientpositive/merge1.q.out @@ -36,12 +36,12 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -56,10 +56,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) + expressions: UDFToInteger($f0) (type: int), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -521,7 +521,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -622,7 +622,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/merge2.q.out b/ql/src/test/results/clientpositive/merge2.q.out index a3a0e8e..b68819e 100644 --- a/ql/src/test/results/clientpositive/merge2.q.out +++ b/ql/src/test/results/clientpositive/merge2.q.out @@ -36,12 +36,12 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -56,10 +56,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) + expressions: UDFToInteger($f0) (type: int), UDFToInteger($f1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -521,7 +521,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -622,7 +622,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/merge3.q.out b/ql/src/test/results/clientpositive/merge3.q.out index b237631..504947d 100644 --- a/ql/src/test/results/clientpositive/merge3.q.out +++ b/ql/src/test/results/clientpositive/merge3.q.out @@ -69,26 +69,18 @@ TOK_CREATETABLE TOK_FROM TOK_TABREF TOK_TABNAME - default merge_src - merge_src TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR - . - TOK_TABLE_OR_COL - merge_src + TOK_TABLE_OR_COL key - key TOK_SELEXPR - . - TOK_TABLE_OR_COL - merge_src + TOK_TABLE_OR_COL value - value STAGE DEPENDENCIES: @@ -112,7 +104,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -242,7 +234,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -ext-10003 + base file name: -ext-10002 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: @@ -296,7 +288,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -ext-10003 + base file name: -ext-10002 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: @@ -2452,7 +2444,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/merge4.q.out b/ql/src/test/results/clientpositive/merge4.q.out index 031376f..c3aa1c1 100644 --- a/ql/src/test/results/clientpositive/merge4.q.out +++ b/ql/src/test/results/clientpositive/merge4.q.out @@ -35,7 +35,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1155,7 +1155,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2776,53 +2776,53 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: srcpart + alias: s-subquery1:_u1-subquery1:srcpart Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1500 Data size: 140124 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 1 - Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: + Select Operator + expressions: key (type: string), value (type: string), hr (type: string) + outputColumnNames: key, value, hr + Statistics: Num rows: 1500 Data size: 388500 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 1 Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part TableScan - alias: src + alias: s-subquery2:_u1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '1' (type: string), '1' (type: string), 'file,' (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, hr Statistics: Num rows: 500 Data size: 129500 Basic stats: COMPLETE Column stats: COMPLETE Union Statistics: Num rows: 1500 Data size: 140124 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 1 - Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: + Select Operator + expressions: key (type: string), value (type: string), hr (type: string) + outputColumnNames: key, value, hr + Statistics: Num rows: 1500 Data size: 388500 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 1 Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 1 - Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part Stage: Stage-7 Conditional Operator @@ -2900,9 +2900,15 @@ POSTHOOK: Input: default@src POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Output: default@nzhang_part@ds=2010-08-15/hr=11 +POSTHOOK: Output: default@nzhang_part@ds=2010-08-15/hr=12 POSTHOOK: Output: default@nzhang_part@ds=2010-08-15/hr=file, -POSTHOOK: Lineage: nzhang_part PARTITION(ds=2010-08-15,hr=file,).key EXPRESSION [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: nzhang_part PARTITION(ds=2010-08-15,hr=file,).value EXPRESSION [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: nzhang_part PARTITION(ds=2010-08-15,hr=11).key EXPRESSION [(srcpart)s-subquery1:_u1-subquery1:srcpart.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: nzhang_part PARTITION(ds=2010-08-15,hr=11).value EXPRESSION [(srcpart)s-subquery1:_u1-subquery1:srcpart.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: nzhang_part PARTITION(ds=2010-08-15,hr=12).key EXPRESSION [(srcpart)s-subquery1:_u1-subquery1:srcpart.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: nzhang_part PARTITION(ds=2010-08-15,hr=12).value EXPRESSION [(srcpart)s-subquery1:_u1-subquery1:srcpart.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: nzhang_part PARTITION(ds=2010-08-15,hr=file,).key EXPRESSION [(srcpart)s-subquery1:_u1-subquery1:srcpart.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: nzhang_part PARTITION(ds=2010-08-15,hr=file,).value EXPRESSION [(srcpart)s-subquery1:_u1-subquery1:srcpart.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: show partitions nzhang_part PREHOOK: type: SHOWPARTITIONS PREHOOK: Input: default@nzhang_part diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition.q.out index da19b32..34515d6 100644 --- a/ql/src/test/results/clientpositive/merge_dynamic_partition.q.out +++ b/ql/src/test/results/clientpositive/merge_dynamic_partition.q.out @@ -71,7 +71,7 @@ STAGE PLANS: Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, hr Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -662,7 +662,7 @@ STAGE PLANS: Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1292,7 +1292,7 @@ STAGE PLANS: Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), '11' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition2.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition2.q.out index 5a2afb0..3d4dd37 100644 --- a/ql/src/test/results/clientpositive/merge_dynamic_partition2.q.out +++ b/ql/src/test/results/clientpositive/merge_dynamic_partition2.q.out @@ -89,7 +89,7 @@ STAGE PLANS: Statistics: Num rows: 87 Data size: 17415 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, hr Statistics: Num rows: 87 Data size: 17415 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out index 86978f3..d8bc3a6 100644 --- a/ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out +++ b/ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out @@ -153,7 +153,7 @@ STAGE PLANS: Statistics: Num rows: 174 Data size: 34830 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 174 Data size: 34830 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out index 86af660..88f77c9 100644 --- a/ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out +++ b/ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out @@ -156,7 +156,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 2.0) = 0.0), 'a1', 'b1') (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, hr Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out index c1468c1..f583f1e 100644 --- a/ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out +++ b/ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out @@ -130,7 +130,7 @@ STAGE PLANS: Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, hr Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/merge_join_1.q.out b/ql/src/test/results/clientpositive/merge_join_1.q.out index ebd13f4..3c53570 100644 --- a/ql/src/test/results/clientpositive/merge_join_1.q.out +++ b/ql/src/test/results/clientpositive/merge_join_1.q.out @@ -156,13 +156,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/mergejoin.q.out b/ql/src/test/results/clientpositive/mergejoin.q.out index cb96ab3..0b8d6a0 100644 --- a/ql/src/test/results/clientpositive/mergejoin.q.out +++ b/ql/src/test/results/clientpositive/mergejoin.q.out @@ -25,14 +25,14 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) @@ -42,30 +42,34 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -279,17 +283,19 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Statistics: Num rows: 275 Data size: 25850 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 275 Data size: 25850 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -305,13 +311,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1348,17 +1358,19 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Statistics: Num rows: 550 Data size: 51700 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 550 Data size: 51700 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1374,13 +1386,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1446,17 +1462,19 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Statistics: Num rows: 550 Data size: 51700 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 550 Data size: 51700 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1472,13 +1490,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1544,17 +1566,19 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Statistics: Num rows: 550 Data size: 51700 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 550 Data size: 51700 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1570,13 +1594,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1685,17 +1713,19 @@ STAGE PLANS: 0 _col1 (type: string) 1 value (type: string) Statistics: Num rows: 302 Data size: 28435 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 302 Data size: 28435 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -1711,13 +1741,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1787,17 +1821,19 @@ STAGE PLANS: 0 value (type: string) 1 value (type: string) Statistics: Num rows: 275 Data size: 25850 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 275 Data size: 25850 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1813,13 +1849,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1897,12 +1937,16 @@ STAGE PLANS: 1 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 133 Data size: 12511 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 133 Data size: 12511 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1953,17 +1997,19 @@ STAGE PLANS: 0 _col0 (type: int) 1 key (type: int) Statistics: Num rows: 279 Data size: 26273 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 279 Data size: 26273 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -1979,13 +2025,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2038,17 +2088,19 @@ STAGE PLANS: 0 value (type: string) 1 value (type: string) Statistics: Num rows: 275 Data size: 25850 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 275 Data size: 25850 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -2064,13 +2116,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2177,17 +2233,19 @@ STAGE PLANS: 0 _col1 (type: string) 1 value (type: string) Statistics: Num rows: 302 Data size: 28435 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 302 Data size: 28435 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -2203,13 +2261,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2289,12 +2351,16 @@ STAGE PLANS: 1 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 133 Data size: 12511 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 133 Data size: 12511 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -2345,17 +2411,19 @@ STAGE PLANS: 0 _col0 (type: int) 1 key (type: int) Statistics: Num rows: 279 Data size: 26273 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 279 Data size: 26273 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -2371,13 +2439,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2497,13 +2569,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce diff --git a/ql/src/test/results/clientpositive/mergejoins.q.out b/ql/src/test/results/clientpositive/mergejoins.q.out index 37761b7..d7350f7 100644 --- a/ql/src/test/results/clientpositive/mergejoins.q.out +++ b/ql/src/test/results/clientpositive/mergejoins.q.out @@ -185,42 +185,51 @@ STAGE PLANS: TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) TableScan - alias: a + alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: @@ -228,21 +237,25 @@ STAGE PLANS: Left Outer Join1 to 2 filter predicates: 0 - 1 {(UDFToDouble(KEY.reducesinkkey0) < UDFToDouble(10))} - 2 + 1 + 2 {(UDFToDouble(VALUE.value) < UDFToDouble(10))} keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 key (type: string) + 1 key (type: string) + 2 key (type: string) + outputColumnNames: key, value, key0, value0, key1, value1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string), key1 (type: string), value1 (type: string) + outputColumnNames: key, value, key0, value0, key1, value1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/metadata_only_queries.q.out b/ql/src/test/results/clientpositive/metadata_only_queries.q.out index 5907f4a..fdcae8a 100644 --- a/ql/src/test/results/clientpositive/metadata_only_queries.q.out +++ b/ql/src/test/results/clientpositive/metadata_only_queries.q.out @@ -194,11 +194,11 @@ STAGE PLANS: alias: stats_tbl Statistics: Num rows: 9999 Data size: 1030908 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s (type: string), bo (type: boolean), bin (type: binary), si (type: smallint), i (type: int), b (type: bigint) - outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 + expressions: 1 (type: int), 0.2 (type: double), s (type: string), bo (type: boolean), bin (type: binary), si (type: smallint), i (type: int), b (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7 Statistics: Num rows: 9999 Data size: 1030908 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), sum(1), sum(0.2), count(1), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) + aggregations: count(), sum($f0), sum($f1), count($f0), count($f2), count($f3), count($f4), count($f5), max($f6), min($f7) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE @@ -210,15 +210,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9 + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: double), $f3 (type: bigint), $f4 (type: bigint), $f5 (type: bigint), $f6 (type: bigint), $f7 (type: bigint), $f8 (type: int), $f9 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9 + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -244,11 +248,11 @@ STAGE PLANS: alias: stats_tbl_part Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s (type: string), bo (type: boolean), bin (type: binary), si (type: smallint), i (type: int), b (type: bigint) - outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 + expressions: 1 (type: int), 0.2 (type: double), s (type: string), bo (type: boolean), bin (type: binary), si (type: smallint), i (type: int), b (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7 Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), sum(1), sum(0.2), count(1), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) + aggregations: count(), sum($f0), sum($f1), count($f0), count($f2), count($f3), count($f4), count($f5), max($f6), min($f7) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE @@ -260,15 +264,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9 + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: double), $f3 (type: bigint), $f4 (type: bigint), $f5 (type: bigint), $f6 (type: bigint), $f7 (type: bigint), $f8 (type: int), $f9 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9 + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -431,10 +439,10 @@ STAGE PLANS: Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ts Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(ts) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -446,15 +454,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/metadataonly1.q.out b/ql/src/test/results/clientpositive/metadataonly1.q.out index 0d758a5..554cbdf 100644 --- a/ql/src/test/results/clientpositive/metadataonly1.q.out +++ b/ql/src/test/results/clientpositive/metadataonly1.q.out @@ -43,10 +43,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -61,29 +61,33 @@ STAGE PLANS: Group By Operator aggregations: max(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: string) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns $f0 + columns.types string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -144,10 +148,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -158,9 +162,9 @@ STAGE PLANS: value expressions: _col0 (type: string) auto parallelism: false Path -> Alias: - -mr-10003default.test1{ds=1} [$hdt$_0:test1] + -mr-10002default.test1{ds=1} [test1] Path -> Partition: - -mr-10003default.test1{ds=1} + -mr-10002default.test1{ds=1} Partition input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -200,35 +204,39 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - -mr-10003default.test1{ds=1} [$hdt$_0:test1] + -mr-10002default.test1{ds=1} [test1] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: string) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns $f0 + columns.types string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -284,11 +292,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0) - keys: _col0 (type: string) + aggregations: count(DISTINCT ds) + keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -299,9 +307,9 @@ STAGE PLANS: tag: -1 auto parallelism: false Path -> Alias: - -mr-10003default.test1{ds=1} [$hdt$_0:test1] + -mr-10002default.test1{ds=1} [test1] Path -> Partition: - -mr-10003default.test1{ds=1} + -mr-10002default.test1{ds=1} Partition input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -341,35 +349,39 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - -mr-10003default.test1{ds=1} [$hdt$_0:test1] + -mr-10002default.test1{ds=1} [test1] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col0:0._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns $f0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -425,10 +437,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -482,35 +494,39 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - /test1/ds=1 [$hdt$_0:test1] + /test1/ds=1 [test1] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns $f0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -599,15 +615,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a2 + alias: b:test1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -618,10 +634,10 @@ STAGE PLANS: value expressions: _col0 (type: string) auto parallelism: false Path -> Alias: - -mr-10005default.test1{ds=1} [$hdt$_0:$hdt$_1:$hdt$_1:a2] - -mr-10006default.test1{ds=2} [$hdt$_0:$hdt$_1:$hdt$_1:a2] + -mr-10004default.test1{ds=1} [b:test1] + -mr-10005default.test1{ds=2} [b:test1] Path -> Partition: - -mr-10005default.test1{ds=1} + -mr-10004default.test1{ds=1} Partition input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -660,7 +676,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test1 name: default.test1 - -mr-10006default.test1{ds=2} + -mr-10005default.test1{ds=2} Partition input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -700,19 +716,19 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - -mr-10005default.test1{ds=1} [$hdt$_0:$hdt$_1:$hdt$_1:a2] - -mr-10006default.test1{ds=2} [$hdt$_0:$hdt$_1:$hdt$_1:a2] + -mr-10004default.test1{ds=1} [b:test1] + -mr-10005default.test1{ds=2} [b:test1] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE + predicate: $f0 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -722,7 +738,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0 + columns $f0 columns.types string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -740,22 +756,22 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: ds (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: ds (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE tag: 0 auto parallelism: false TableScan GatherStats: false Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: $f0 (type: string) + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE tag: 1 auto parallelism: false Path -> Alias: @@ -763,11 +779,11 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10004 + base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0 + columns $f0 columns.types string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -776,7 +792,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0 + columns $f0 columns.types string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -862,8 +878,8 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - /test1/ds=1 [$hdt$_0:$hdt$_0:a2] - /test1/ds=2 [$hdt$_0:$hdt$_0:a2] + /test1/ds=1 [a2] + /test1/ds=2 [a2] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: @@ -871,31 +887,33 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 ds (type: string) + 1 $f0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -913,7 +931,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10003 + base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: @@ -938,29 +956,33 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns $f0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -1053,11 +1075,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: ds, hr Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT hr) + keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1069,11 +1091,11 @@ STAGE PLANS: tag: -1 auto parallelism: false Path -> Alias: - -mr-10003default.test2{ds=1, hr=1} [$hdt$_0:test2] - -mr-10004default.test2{ds=1, hr=2} [$hdt$_0:test2] - -mr-10005default.test2{ds=1, hr=3} [$hdt$_0:test2] + -mr-10002default.test2{ds=1, hr=1} [test2] + -mr-10003default.test2{ds=1, hr=2} [test2] + -mr-10004default.test2{ds=1, hr=3} [test2] Path -> Partition: - -mr-10003default.test2{ds=1, hr=1} + -mr-10002default.test2{ds=1, hr=1} Partition input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1113,7 +1135,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 - -mr-10004default.test2{ds=1, hr=2} + -mr-10003default.test2{ds=1, hr=2} Partition input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1153,7 +1175,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 - -mr-10005default.test2{ds=1, hr=3} + -mr-10004default.test2{ds=1, hr=3} Partition input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1194,38 +1216,42 @@ STAGE PLANS: name: default.test2 name: default.test2 Truncated Path -> Alias: - -mr-10003default.test2{ds=1, hr=1} [$hdt$_0:test2] - -mr-10004default.test2{ds=1, hr=2} [$hdt$_0:test2] - -mr-10005default.test2{ds=1, hr=3} [$hdt$_0:test2] + -mr-10002default.test2{ds=1, hr=1} [test2] + -mr-10003default.test2{ds=1, hr=2} [test2] + -mr-10004default.test2{ds=1, hr=3} [test2] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: ds, $f1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: ds (type: string), $f1 (type: bigint) + outputColumnNames: ds, $f1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1 - columns.types string:bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns ds,$f1 + columns.types string:bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -1291,11 +1317,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: ds, hr Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(hr) + keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1434,38 +1460,42 @@ STAGE PLANS: name: default.test2 name: default.test2 Truncated Path -> Alias: - /test2/ds=1/hr=1 [$hdt$_0:test2] - /test2/ds=1/hr=2 [$hdt$_0:test2] - /test2/ds=1/hr=3 [$hdt$_0:test2] + /test2/ds=1/hr=1 [test2] + /test2/ds=1/hr=2 [test2] + /test2/ds=1/hr=3 [test2] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: ds, $f1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: ds (type: string), $f1 (type: bigint) + outputColumnNames: ds, $f1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1 - columns.types string:bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns ds,$f1 + columns.types string:bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -1524,10 +1554,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -1538,10 +1568,10 @@ STAGE PLANS: value expressions: _col0 (type: string) auto parallelism: false Path -> Alias: - -mr-10003default.test1{ds=1} [$hdt$_0:test1] - -mr-10004default.test1{ds=2} [$hdt$_0:test1] + -mr-10002default.test1{ds=1} [test1] + -mr-10003default.test1{ds=2} [test1] Path -> Partition: - -mr-10003default.test1{ds=1} + -mr-10002default.test1{ds=1} Partition input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1580,7 +1610,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test1 name: default.test1 - -mr-10004default.test1{ds=2} + -mr-10003default.test1{ds=2} Partition input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1620,36 +1650,40 @@ STAGE PLANS: name: default.test1 name: default.test1 Truncated Path -> Alias: - -mr-10003default.test1{ds=1} [$hdt$_0:test1] - -mr-10004default.test1{ds=2} [$hdt$_0:test1] + -mr-10002default.test1{ds=1} [test1] + -mr-10003default.test1{ds=2} [test1] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: string) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns $f0 + columns.types string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -1764,11 +1798,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: ds, hr Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT hr) + keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1780,13 +1814,13 @@ STAGE PLANS: tag: -1 auto parallelism: false Path -> Alias: - -mr-10003default.test2{ds=01_10_10, hr=01} [$hdt$_0:test2] - -mr-10004default.test2{ds=01_10_20, hr=02} [$hdt$_0:test2] - -mr-10005default.test2{ds=1, hr=1} [$hdt$_0:test2] - -mr-10006default.test2{ds=1, hr=2} [$hdt$_0:test2] - -mr-10007default.test2{ds=1, hr=3} [$hdt$_0:test2] + -mr-10002default.test2{ds=01_10_10, hr=01} [test2] + -mr-10003default.test2{ds=01_10_20, hr=02} [test2] + -mr-10004default.test2{ds=1, hr=1} [test2] + -mr-10005default.test2{ds=1, hr=2} [test2] + -mr-10006default.test2{ds=1, hr=3} [test2] Path -> Partition: - -mr-10003default.test2{ds=01_10_10, hr=01} + -mr-10002default.test2{ds=01_10_10, hr=01} Partition input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1826,7 +1860,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 - -mr-10004default.test2{ds=01_10_20, hr=02} + -mr-10003default.test2{ds=01_10_20, hr=02} Partition input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1866,7 +1900,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 - -mr-10005default.test2{ds=1, hr=1} + -mr-10004default.test2{ds=1, hr=1} Partition input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1906,7 +1940,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 - -mr-10006default.test2{ds=1, hr=2} + -mr-10005default.test2{ds=1, hr=2} Partition input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1946,7 +1980,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 - -mr-10007default.test2{ds=1, hr=3} + -mr-10006default.test2{ds=1, hr=3} Partition input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1987,40 +2021,44 @@ STAGE PLANS: name: default.test2 name: default.test2 Truncated Path -> Alias: - -mr-10003default.test2{ds=01_10_10, hr=01} [$hdt$_0:test2] - -mr-10004default.test2{ds=01_10_20, hr=02} [$hdt$_0:test2] - -mr-10005default.test2{ds=1, hr=1} [$hdt$_0:test2] - -mr-10006default.test2{ds=1, hr=2} [$hdt$_0:test2] - -mr-10007default.test2{ds=1, hr=3} [$hdt$_0:test2] + -mr-10002default.test2{ds=01_10_10, hr=01} [test2] + -mr-10003default.test2{ds=01_10_20, hr=02} [test2] + -mr-10004default.test2{ds=1, hr=1} [test2] + -mr-10005default.test2{ds=1, hr=2} [test2] + -mr-10006default.test2{ds=1, hr=3} [test2] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: ds, $f1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: ds (type: string), $f1 (type: bigint) + outputColumnNames: ds, $f1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1 - columns.types string:bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns ds,$f1 + columns.types string:bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/multiMapJoin1.q.out b/ql/src/test/results/clientpositive/multiMapJoin1.q.out index 8548fc7..c5cb194 100644 --- a/ql/src/test/results/clientpositive/multiMapJoin1.q.out +++ b/ql/src/test/results/clientpositive/multiMapJoin1.q.out @@ -155,8 +155,8 @@ select * from POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@bigtbl -POSTHOOK: Lineage: bigtbl.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: bigtbl.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: bigtbl.key EXPRESSION [(src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery2:subq-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:subq-subquery2:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: bigtbl.value EXPRESSION [(src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery2:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery1-subquery2:subq-subquery1-subquery2:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery2:subq-subquery2:src.FieldSchema(name:value, type:string, comment:default), ] RUN: Stage-1:MAPRED RUN: Stage-7:CONDITIONAL RUN: Stage-4:MOVE @@ -236,22 +236,28 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col1 Statistics: Num rows: 1375 Data size: 14608 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 value (type: string) - Statistics: Num rows: 1512 Data size: 16068 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col1 + Statistics: Num rows: 1375 Data size: 14608 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 value (type: string) + Statistics: Num rows: 1512 Data size: 16068 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 1512 Data size: 16068 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -260,13 +266,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -379,22 +389,28 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col1 Statistics: Num rows: 1375 Data size: 14608 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 value (type: string) - Statistics: Num rows: 1512 Data size: 16068 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col1 + Statistics: Num rows: 1375 Data size: 14608 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 value (type: string) + Statistics: Num rows: 1512 Data size: 16068 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 1512 Data size: 16068 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -403,13 +419,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -526,26 +546,34 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col1 Statistics: Num rows: 1375 Data size: 14608 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 value (type: string) - outputColumnNames: _col3 - Statistics: Num rows: 1512 Data size: 16068 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col3 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col1 + Statistics: Num rows: 1375 Data size: 14608 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 value (type: string) + outputColumnNames: _col3 Statistics: Num rows: 1512 Data size: 16068 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: _col3 (type: string) + outputColumnNames: _col3 Statistics: Num rows: 1512 Data size: 16068 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Group By Operator + aggregations: count() + keys: _col3 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1512 Data size: 16068 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1512 Data size: 16068 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -677,9 +705,9 @@ select * from POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@bigtbl -POSTHOOK: Lineage: bigtbl.key1 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: bigtbl.key2 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: bigtbl.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: bigtbl.key1 EXPRESSION [(src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery2:subq-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:subq-subquery2:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: bigtbl.key2 EXPRESSION [(src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery2:subq-subquery1-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:subq-subquery2:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: bigtbl.value EXPRESSION [(src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery1-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery1-subquery2:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery1-subquery1-subquery2:subq-subquery1-subquery1-subquery2:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery1-subquery2:subq-subquery1-subquery2:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery2:subq-subquery2:src.FieldSchema(name:value, type:string, comment:default), ] RUN: Stage-1:MAPRED RUN: Stage-7:CONDITIONAL RUN: Stage-4:MOVE @@ -994,13 +1022,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-23 Map Reduce Local Work @@ -1672,13 +1704,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2000,13 +2036,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2406,13 +2446,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-23 Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/multiMapJoin2.q.out b/ql/src/test/results/clientpositive/multiMapJoin2.q.out index 2cbef2e..f137091 100644 --- a/ql/src/test/results/clientpositive/multiMapJoin2.q.out +++ b/ql/src/test/results/clientpositive/multiMapJoin2.q.out @@ -23,101 +23,117 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - null-subquery1:$hdt$_0-subquery1:$hdt$_1:y1 + null-subquery1:tmp-subquery1:y1 Fetch Operator limit: -1 - null-subquery2:$hdt$_0-subquery2:$hdt$_1:y1 + null-subquery2:tmp-subquery2:y2 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - null-subquery1:$hdt$_0-subquery1:$hdt$_1:y1 + null-subquery1:tmp-subquery1:y1 TableScan - alias: y1 + alias: null-subquery1:tmp-subquery1:y1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - null-subquery2:$hdt$_0-subquery2:$hdt$_1:y1 + 0 key (type: string) + 1 key (type: string) + null-subquery2:tmp-subquery2:y2 TableScan - alias: y1 + alias: null-subquery2:tmp-subquery2:y2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: x1 + alias: null-subquery1:tmp-subquery1:x1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Union Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x1 + alias: null-subquery2:tmp-subquery2:x2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Union Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -266,78 +282,82 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - null-subquery2:$hdt$_0-subquery2:$hdt$_1:y1 + null-subquery2:tmp-subquery2:y2 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - null-subquery2:$hdt$_0-subquery2:$hdt$_1:y1 + null-subquery2:tmp-subquery2:y2 TableScan - alias: y1 + alias: null-subquery2:tmp-subquery2:y2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-7 Map Reduce Map Operator Tree: TableScan - alias: x1 + alias: null-subquery2:tmp-subquery2:x2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - null-subquery1:$hdt$_0-subquery1:$hdt$_1:y1 + null-subquery1:tmp-subquery1:y1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - null-subquery1:$hdt$_0-subquery1:$hdt$_1:y1 + null-subquery1:tmp-subquery1:y1 TableScan - alias: y1 + alias: null-subquery1:tmp-subquery1:y1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-2 Map Reduce @@ -345,40 +365,52 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x1 + alias: null-subquery1:tmp-subquery1:x1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Union Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -523,14 +555,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x1 + alias: null-subquery1:tmp-subquery1:x1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -543,7 +575,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -555,25 +587,25 @@ STAGE PLANS: Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - null-subquery2:$hdt$_0-subquery2:$hdt$_1:x1 + null-subquery2:tmp-subquery2:y2 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - null-subquery2:$hdt$_0-subquery2:$hdt$_1:x1 + null-subquery2:tmp-subquery2:y2 TableScan - alias: x1 + alias: null-subquery2:tmp-subquery2:y2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-2 Map Reduce @@ -581,40 +613,52 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 287 Data size: 3012 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 287 Data size: 3012 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Statistics: Num rows: 287 Data size: 3012 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x2 + alias: null-subquery2:tmp-subquery2:x2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 287 Data size: 3012 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Union Statistics: Num rows: 287 Data size: 3012 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 287 Data size: 3012 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Statistics: Num rows: 287 Data size: 3012 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 287 Data size: 3012 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -761,64 +805,68 @@ STAGE PLANS: Stage: Stage-17 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y1 + tmp2:y2 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y1 + tmp2:y2 TableScan - alias: y1 + alias: tmp2:y2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: x1 + alias: tmp2:x2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Select Operator + expressions: key (type: string) + outputColumnNames: $f0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -833,16 +881,16 @@ STAGE PLANS: Stage: Stage-15 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$INTNAME1 + $INTNAME1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$INTNAME1 + $INTNAME1 TableScan HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 $f0 (type: string) + 1 $f0 (type: string) Stage: Stage-10 Map Reduce @@ -852,22 +900,26 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f0 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: $f0 (type: string) + outputColumnNames: $f0 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count() + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -886,27 +938,31 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 75 Data size: 800 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 75 Data size: 800 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-5 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: bigint) + key expressions: $f0 (type: string), $f1 (type: bigint) sort order: ++ Statistics: Num rows: 75 Data size: 800 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 75 Data size: 800 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -919,16 +975,16 @@ STAGE PLANS: Stage: Stage-16 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$INTNAME + $INTNAME Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$INTNAME + $INTNAME TableScan HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 $f0 (type: string) + 1 $f0 (type: string) Stage: Stage-11 Map Reduce @@ -938,22 +994,26 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f0 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: $f0 (type: string) + outputColumnNames: $f0 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count() + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -962,99 +1022,107 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f0 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: $f0 (type: string) + outputColumnNames: $f0 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count() + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-18 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_2:y1 + tmp1:y1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_2:y1 + tmp1:y1 TableScan - alias: y1 + alias: tmp1:y1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-8 Map Reduce Map Operator Tree: TableScan - alias: x1 + alias: tmp1:x1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Select Operator + expressions: key (type: string) + outputColumnNames: $f0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1154,112 +1222,121 @@ GROUP BY tmp1.key ORDER BY key, cnt POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-9 is a root stage - Stage-2 depends on stages: Stage-9 + Stage-10 is a root stage + Stage-2 depends on stages: Stage-10 Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-4 STAGE PLANS: - Stage: Stage-9 + Stage: Stage-10 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y1 + tmp1:y1 Fetch Operator limit: -1 - $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_2:y1 + tmp2:y2 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:y1 + tmp1:y1 TableScan - alias: y1 + alias: tmp1:y1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - $hdt$_0:$hdt$_1:$hdt$_1:$hdt$_2:y1 + 0 key (type: string) + 1 key (type: string) + tmp2:y2 TableScan - alias: y1 + alias: tmp2:y2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: x1 + alias: tmp2:x2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Select Operator + expressions: key (type: string) + outputColumnNames: $f0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x1 + alias: tmp1:x1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Select Operator + expressions: key (type: string) + outputColumnNames: $f0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1268,7 +1345,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE @@ -1276,16 +1353,18 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator + Select Operator + expressions: $f0 (type: string) + outputColumnNames: $f0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) - mode: complete + keys: $f0 (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator @@ -1297,7 +1376,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE @@ -1305,16 +1384,18 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 $f0 (type: string) + 1 $f0 (type: string) + outputColumnNames: $f0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator + Select Operator + expressions: $f0 (type: string) + outputColumnNames: $f0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) - mode: complete + keys: $f0 (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator @@ -1329,13 +1410,41 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: bigint) + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-4 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: $f0 (type: string), $f1 (type: bigint) sort order: ++ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false @@ -1379,9 +1488,10 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 #### A masked pattern was here #### -RUN: Stage-9:MAPREDLOCAL +RUN: Stage-10:MAPREDLOCAL RUN: Stage-2:MAPRED RUN: Stage-3:MAPRED +RUN: Stage-4:MAPRED 128 1 146 1 150 1 @@ -1436,35 +1546,35 @@ GROUP BY tmp1.key ORDER BY key, cnt POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-7 is a root stage - Stage-10 depends on stages: Stage-2, Stage-7 , consists of Stage-12, Stage-13, Stage-3 - Stage-12 has a backup stage: Stage-3 + Stage-1 is a root stage + Stage-10 depends on stages: Stage-1, Stage-6 , consists of Stage-12, Stage-13, Stage-2 + Stage-12 has a backup stage: Stage-2 Stage-8 depends on stages: Stage-12 - Stage-4 depends on stages: Stage-3, Stage-8, Stage-9 - Stage-5 depends on stages: Stage-4 - Stage-13 has a backup stage: Stage-3 + Stage-3 depends on stages: Stage-2, Stage-8, Stage-9 + Stage-4 depends on stages: Stage-3 + Stage-13 has a backup stage: Stage-2 Stage-9 depends on stages: Stage-13 - Stage-3 + Stage-2 Stage-14 is a root stage - Stage-2 depends on stages: Stage-14 - Stage-0 depends on stages: Stage-5 + Stage-6 depends on stages: Stage-14 + Stage-0 depends on stages: Stage-4 STAGE PLANS: - Stage: Stage-7 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: x1 + alias: tmp1:x1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE @@ -1477,7 +1587,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1492,16 +1602,16 @@ STAGE PLANS: Stage: Stage-12 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$INTNAME1 + $INTNAME1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$INTNAME1 + $INTNAME1 TableScan HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 $f0 (type: string) Stage: Stage-8 Map Reduce @@ -1511,17 +1621,17 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 $f0 (type: string) + outputColumnNames: key Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + expressions: key (type: string) + outputColumnNames: $f0 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE @@ -1534,7 +1644,7 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-4 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan @@ -1549,27 +1659,31 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 75 Data size: 800 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 75 Data size: 800 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-5 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: bigint) + key expressions: $f0 (type: string), $f1 (type: bigint) sort order: ++ Statistics: Num rows: 75 Data size: 800 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 75 Data size: 800 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1582,16 +1696,16 @@ STAGE PLANS: Stage: Stage-13 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$INTNAME + $INTNAME Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$INTNAME + $INTNAME TableScan HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 $f0 (type: string) Stage: Stage-9 Map Reduce @@ -1601,17 +1715,17 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 $f0 (type: string) + outputColumnNames: key Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + expressions: key (type: string) + outputColumnNames: $f0 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE @@ -1624,37 +1738,37 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-3 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: $f0 (type: string) + Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 $f0 (type: string) + outputColumnNames: key Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + expressions: key (type: string) + outputColumnNames: $f0 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE @@ -1668,64 +1782,68 @@ STAGE PLANS: Stage: Stage-14 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:x1 + tmp2:y2 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:x1 + tmp2:y2 TableScan - alias: x1 + alias: tmp2:y2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) - Stage: Stage-2 + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan - alias: x2 + alias: tmp2:x2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Select Operator + expressions: key (type: string) + outputColumnNames: $f0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1768,14 +1886,14 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 #### A masked pattern was here #### -RUN: Stage-7:MAPRED +RUN: Stage-1:MAPRED RUN: Stage-14:MAPREDLOCAL -RUN: Stage-2:MAPRED +RUN: Stage-6:MAPRED RUN: Stage-10:CONDITIONAL -RUN: Stage-13:MAPREDLOCAL -RUN: Stage-9:MAPRED +RUN: Stage-12:MAPREDLOCAL +RUN: Stage-8:MAPRED +RUN: Stage-3:MAPRED RUN: Stage-4:MAPRED -RUN: Stage-5:MAPRED 128 1 146 1 150 1 @@ -1825,7 +1943,8 @@ ORDER BY key, cnt POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-7 is a root stage - Stage-2 depends on stages: Stage-7 + Stage-1 depends on stages: Stage-7 + Stage-2 depends on stages: Stage-1 Stage-3 depends on stages: Stage-2 Stage-0 depends on stages: Stage-3 @@ -1833,41 +1952,41 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:x1 + tmp2:y2 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_0:$hdt$_1:x1 + tmp2:y2 TableScan - alias: x1 + alias: tmp2:y2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) - Stage: Stage-2 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: x1 + alias: tmp1:x1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE @@ -1877,33 +1996,37 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE TableScan - alias: x2 + alias: tmp2:x2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Select Operator + expressions: key (type: string) + outputColumnNames: $f0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1912,7 +2035,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 144 Data size: 1510 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 288 Data size: 3020 Basic stats: COMPLETE Column stats: NONE @@ -1920,32 +2043,30 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 $f0 (type: string) + outputColumnNames: key Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + expressions: key (type: string) + outputColumnNames: $f0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count() + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 144 Data size: 1510 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 288 Data size: 3020 Basic stats: COMPLETE Column stats: NONE @@ -1953,41 +2074,67 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 + 0 key (type: string) + 1 $f0 (type: string) + outputColumnNames: key Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 + expressions: key (type: string) + outputColumnNames: $f0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count() + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: bigint) + key expressions: $f0 (type: string), $f1 (type: bigint) sort order: ++ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false @@ -2032,6 +2179,7 @@ POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 #### A masked pattern was here #### RUN: Stage-7:MAPREDLOCAL +RUN: Stage-1:MAPRED RUN: Stage-2:MAPRED RUN: Stage-3:MAPRED 128 1 @@ -2139,15 +2287,17 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Statistics: Num rows: 69 Data size: 698 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 69 Data size: 698 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -2156,13 +2306,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2218,75 +2372,84 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-15 is a root stage Stage-4 depends on stages: Stage-15 - Stage-14 depends on stages: Stage-4, Stage-8 + Stage-14 depends on stages: Stage-4, Stage-12 Stage-2 depends on stages: Stage-14 - Stage-16 is a root stage - Stage-8 depends on stages: Stage-16 + Stage-17 is a root stage + Stage-8 depends on stages: Stage-17 + Stage-16 depends on stages: Stage-8 + Stage-12 depends on stages: Stage-16 Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-15 Map Reduce Local Work Alias -> Map Local Tables: - null-subquery1:$hdt$_0-subquery1:$hdt$_1:$hdt$_1:$hdt$_1:a + null-subquery1:x-subquery1:tmp:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - null-subquery1:$hdt$_0-subquery1:$hdt$_1:$hdt$_1:$hdt$_1:a + null-subquery1:x-subquery1:tmp:a TableScan - alias: a + alias: null-subquery1:x-subquery1:tmp:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: a + alias: null-subquery1:x-subquery1:tmp:b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: $f0 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 69 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2297,57 +2460,35 @@ STAGE PLANS: Stage: Stage-14 Map Reduce Local Work Alias -> Map Local Tables: - null-subquery1:$hdt$_0-subquery1:$hdt$_0:a - Fetch Operator - limit: -1 - null-subquery2:$hdt$_0-subquery2:$hdt$_0:a + null-subquery1:x-subquery1:c Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - null-subquery1:$hdt$_0-subquery1:$hdt$_0:a + null-subquery1:x-subquery1:c TableScan - alias: a + alias: null-subquery1:x-subquery1:c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - null-subquery2:$hdt$_0-subquery2:$hdt$_0:a - TableScan - alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 $f0 (type: string) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Union + Union + Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2361,84 +2502,99 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 $f0 (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Union Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work - Stage: Stage-16 + Stage: Stage-17 Map Reduce Local Work Alias -> Map Local Tables: - null-subquery2:$hdt$_0-subquery2:$hdt$_1:$hdt$_1:$hdt$_1:a + null-subquery2:x-subquery2:tmp:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - null-subquery2:$hdt$_0-subquery2:$hdt$_1:$hdt$_1:$hdt$_1:a + null-subquery2:x-subquery2:tmp:a TableScan - alias: a + alias: null-subquery2:x-subquery2:tmp:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-8 Map Reduce Map Operator Tree: TableScan - alias: a + alias: null-subquery2:x-subquery2:tmp:b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: $f0 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 69 Data size: 732 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2446,6 +2602,54 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Stage: Stage-16 + Map Reduce Local Work + Alias -> Map Local Tables: + null-subquery2:x-subquery2:c + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + null-subquery2:x-subquery2:c + TableScan + alias: null-subquery2:x-subquery2:c + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 key (type: string) + 1 $f0 (type: string) + + Stage: Stage-12 + Map Reduce + Map Operator Tree: + TableScan + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 $f0 (type: string) + outputColumnNames: key + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Local Work: + Map Reduce Local Work + Stage: Stage-0 Fetch Operator limit: -1 @@ -2477,9 +2681,11 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### RUN: Stage-15:MAPREDLOCAL -RUN: Stage-16:MAPREDLOCAL +RUN: Stage-17:MAPREDLOCAL RUN: Stage-4:MAPRED RUN: Stage-8:MAPRED +RUN: Stage-16:MAPREDLOCAL +RUN: Stage-12:MAPRED RUN: Stage-14:MAPREDLOCAL RUN: Stage-2:MAPRED 0 diff --git a/ql/src/test/results/clientpositive/multi_column_in.q.out b/ql/src/test/results/clientpositive/multi_column_in.q.out index e0ec848..b904339 100644 --- a/ql/src/test/results/clientpositive/multi_column_in.q.out +++ b/ql/src/test/results/clientpositive/multi_column_in.q.out @@ -123,7 +123,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: empno (type: int), deptno (type: int), empname (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: empno, deptno, empname Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -161,7 +161,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: empno (type: int), deptno (type: int), empname (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: empno, deptno, empname Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -243,7 +243,7 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: empno (type: int), deptno (type: int), empname (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: empno, deptno, empname Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/multi_insert.q.out b/ql/src/test/results/clientpositive/multi_insert.q.out index f8fc172..7f63db9 100644 --- a/ql/src/test/results/clientpositive/multi_insert.q.out +++ b/ql/src/test/results/clientpositive/multi_insert.q.out @@ -757,11 +757,15 @@ STAGE PLANS: Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE @@ -773,14 +777,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE @@ -789,14 +797,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 Stage: Stage-0 Move Operator @@ -907,11 +919,15 @@ STAGE PLANS: Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE @@ -923,14 +939,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE @@ -939,14 +959,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 Stage: Stage-8 Conditional Operator @@ -1125,11 +1149,15 @@ STAGE PLANS: Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE @@ -1141,14 +1169,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE @@ -1157,14 +1189,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 Stage: Stage-0 Move Operator @@ -1275,11 +1311,15 @@ STAGE PLANS: Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE @@ -1291,14 +1331,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE @@ -1307,14 +1351,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 Stage: Stage-8 Conditional Operator @@ -1499,25 +1547,33 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 10) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1530,25 +1586,33 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 10) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 Stage: Stage-0 Move Operator @@ -1691,25 +1755,33 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 10) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1722,25 +1794,33 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 10) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 Stage: Stage-8 Conditional Operator @@ -1951,25 +2031,33 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 10) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1982,25 +2070,33 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 10) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 Stage: Stage-0 Move Operator @@ -2143,25 +2239,33 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 10) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -2174,25 +2278,33 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 10) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 Stage: Stage-8 Conditional Operator diff --git a/ql/src/test/results/clientpositive/multi_insert_gby.q.out b/ql/src/test/results/clientpositive/multi_insert_gby.q.out index 7c5e589..e419c87 100644 --- a/ql/src/test/results/clientpositive/multi_insert_gby.q.out +++ b/ql/src/test/results/clientpositive/multi_insert_gby.q.out @@ -49,11 +49,15 @@ STAGE PLANS: Filter Operator predicate: ((key > 500) or (key > 450)) (type: boolean) Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/multi_insert_gby2.q.out b/ql/src/test/results/clientpositive/multi_insert_gby2.q.out index f4baf04..9c20dbb 100644 --- a/ql/src/test/results/clientpositive/multi_insert_gby2.q.out +++ b/ql/src/test/results/clientpositive/multi_insert_gby2.q.out @@ -99,14 +99,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: double) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e2 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e2 Stage: Stage-0 Move Operator diff --git a/ql/src/test/results/clientpositive/multi_insert_gby3.q.out b/ql/src/test/results/clientpositive/multi_insert_gby3.q.out index 6ee003b..db291e2 100644 --- a/ql/src/test/results/clientpositive/multi_insert_gby3.q.out +++ b/ql/src/test/results/clientpositive/multi_insert_gby3.q.out @@ -1775,30 +1775,38 @@ STAGE PLANS: expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: double), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: double), _col2 (type: string) - mode: complete - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), UDFToDouble(_col3) (type: double) - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col0 (type: string), _col1 (type: double), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: double), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(DISTINCT _col1) + keys: _col0 (type: string), _col1 (type: double), _col2 (type: string) + mode: complete + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), UDFToDouble(_col3) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e3 + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e3 Stage: Stage-4 Map Reduce diff --git a/ql/src/test/results/clientpositive/multi_insert_lateral_view.q.out b/ql/src/test/results/clientpositive/multi_insert_lateral_view.q.out index 4723153..1cd58ef 100644 --- a/ql/src/test/results/clientpositive/multi_insert_lateral_view.q.out +++ b/ql/src/test/results/clientpositive/multi_insert_lateral_view.q.out @@ -389,26 +389,8 @@ STAGE PLANS: Lateral View Join Operator outputColumnNames: _col0, _col5 Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col5) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double) - Select Operator - expressions: array((key + 1),(key + 2)) (type: array) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - UDTF Operator - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - function name: explode - Lateral View Join Operator + Select Operator + expressions: _col0 (type: string), _col5 (type: double) outputColumnNames: _col0, _col5 Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -423,6 +405,32 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double) + Select Operator + expressions: array((key + 1),(key + 2)) (type: array) + outputColumnNames: _col0 + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + function name: explode + Lateral View Join Operator + outputColumnNames: _col0, _col5 + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col5 (type: double) + outputColumnNames: _col0, _col5 + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col5) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: double) Lateral View Forward Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Select Operator @@ -432,26 +440,8 @@ STAGE PLANS: Lateral View Join Operator outputColumnNames: _col0, _col5 Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col5) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Select Operator - expressions: array((key + 3),(key + 4)) (type: array) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - UDTF Operator - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - function name: explode - Lateral View Join Operator + Select Operator + expressions: _col0 (type: string), _col5 (type: double) outputColumnNames: _col0, _col5 Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -466,6 +456,32 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: array((key + 3),(key + 4)) (type: array) + outputColumnNames: _col0 + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + function name: explode + Lateral View Join Operator + outputColumnNames: _col0, _col5 + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col5 (type: double) + outputColumnNames: _col0, _col5 + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col5) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) @@ -473,14 +489,18 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_lv1 + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_lv1 Stage: Stage-0 Move Operator @@ -512,14 +532,18 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_lv2 + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_lv2 Stage: Stage-1 Move Operator @@ -636,26 +660,8 @@ STAGE PLANS: Lateral View Join Operator outputColumnNames: _col0, _col5 Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col5) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double) - Select Operator - expressions: array((key + 1),(key + 2)) (type: array) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - UDTF Operator - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - function name: explode - Lateral View Join Operator + Select Operator + expressions: _col0 (type: string), _col5 (type: double) outputColumnNames: _col0, _col5 Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -670,15 +676,45 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double) + Select Operator + expressions: array((key + 1),(key + 2)) (type: array) + outputColumnNames: _col0 + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + function name: explode + Lateral View Join Operator + outputColumnNames: _col0, _col5 + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col5 (type: double) + outputColumnNames: _col0, _col5 + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col5) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: double) Filter Operator predicate: ((key < 200) or (key > 200)) (type: boolean) Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) @@ -686,14 +722,18 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_lv1 + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_lv1 Stage: Stage-0 Move Operator @@ -730,14 +770,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_lv2 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_lv2 Filter Operator predicate: (KEY._col0 < 200) (type: boolean) Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE @@ -747,14 +791,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_lv3 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_lv3 Stage: Stage-1 Move Operator @@ -1017,14 +1065,18 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: double), _col1 (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_lv1 + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_lv1 Stage: Stage-0 Move Operator @@ -1055,14 +1107,18 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: double), _col1 (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_lv2 + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_lv2 Stage: Stage-1 Move Operator @@ -1093,14 +1149,18 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_lv3 + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_lv3 Stage: Stage-2 Move Operator @@ -1266,17 +1326,21 @@ STAGE PLANS: Lateral View Join Operator outputColumnNames: _col0, _col5 Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(DISTINCT _col5) - keys: _col0 (type: string), _col5 (type: double) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: _col0 (type: string), _col5 (type: double) + outputColumnNames: _col0, _col5 Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double) - sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: sum(DISTINCT _col5) + keys: _col0 (type: string), _col5 (type: double) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: double) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: array((key + 1),(key + 2)) (type: array) outputColumnNames: _col0 @@ -1287,17 +1351,21 @@ STAGE PLANS: Lateral View Join Operator outputColumnNames: _col0, _col5 Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(DISTINCT _col5) - keys: _col0 (type: string), _col5 (type: double) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: _col0 (type: string), _col5 (type: double) + outputColumnNames: _col0, _col5 Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double) - sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: sum(DISTINCT _col5) + keys: _col0 (type: string), _col5 (type: double) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: double) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE Lateral View Forward Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Select Operator @@ -1307,26 +1375,8 @@ STAGE PLANS: Lateral View Join Operator outputColumnNames: _col0, _col5 Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(DISTINCT _col5) - keys: _col0 (type: string), _col5 (type: double) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Select Operator - expressions: array((key + 3),(key + 4)) (type: array) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - UDTF Operator - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - function name: explode - Lateral View Join Operator + Select Operator + expressions: _col0 (type: string), _col5 (type: double) outputColumnNames: _col0, _col5 Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -1341,15 +1391,45 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: array((key + 3),(key + 4)) (type: array) + outputColumnNames: _col0 + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + function name: explode + Lateral View Join Operator + outputColumnNames: _col0, _col5 + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col5 (type: double) + outputColumnNames: _col0, _col5 + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(DISTINCT _col5) + keys: _col0 (type: string), _col5 (type: double) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((key < 200) or (key > 200)) (type: boolean) Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 62 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Reduce Operator Tree: Group By Operator aggregations: sum(DISTINCT KEY._col1:0._col0) @@ -1357,14 +1437,18 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_lv1 + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_lv1 Stage: Stage-0 Move Operator @@ -1395,14 +1479,18 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_lv2 + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_lv2 Stage: Stage-1 Move Operator @@ -1438,14 +1526,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_lv3 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_lv3 Filter Operator predicate: (KEY._col1:0._col0 < 200) (type: boolean) Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE @@ -1455,14 +1547,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_lv4 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_lv4 Stage: Stage-2 Move Operator diff --git a/ql/src/test/results/clientpositive/multi_insert_mixed.q.out b/ql/src/test/results/clientpositive/multi_insert_mixed.q.out index aaf9346..116d9e4 100644 --- a/ql/src/test/results/clientpositive/multi_insert_mixed.q.out +++ b/ql/src/test/results/clientpositive/multi_insert_mixed.q.out @@ -113,12 +113,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -173,12 +177,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-7 Map Reduce diff --git a/ql/src/test/results/clientpositive/multi_insert_move_tasks_share_dependencies.q.out b/ql/src/test/results/clientpositive/multi_insert_move_tasks_share_dependencies.q.out index 81d9808..e2f0675 100644 --- a/ql/src/test/results/clientpositive/multi_insert_move_tasks_share_dependencies.q.out +++ b/ql/src/test/results/clientpositive/multi_insert_move_tasks_share_dependencies.q.out @@ -774,11 +774,15 @@ STAGE PLANS: Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE @@ -790,14 +794,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE @@ -806,14 +814,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 Stage: Stage-4 Dependency Collection @@ -928,11 +940,15 @@ STAGE PLANS: Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE @@ -944,14 +960,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE @@ -960,14 +980,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 Stage: Stage-9 Conditional Operator @@ -1150,11 +1174,15 @@ STAGE PLANS: Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE @@ -1166,14 +1194,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE @@ -1182,14 +1214,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 Stage: Stage-4 Dependency Collection @@ -1304,11 +1340,15 @@ STAGE PLANS: Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE @@ -1320,14 +1360,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE @@ -1336,14 +1380,18 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 Stage: Stage-9 Conditional Operator @@ -1532,25 +1580,33 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 10) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1563,25 +1619,33 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 10) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 Stage: Stage-4 Dependency Collection @@ -1728,25 +1792,33 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 10) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1759,25 +1831,33 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 10) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 Stage: Stage-9 Conditional Operator @@ -1992,25 +2072,33 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 10) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -2023,25 +2111,33 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 10) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 Stage: Stage-4 Dependency Collection @@ -2188,25 +2284,33 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 10) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -2219,25 +2323,33 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 10) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1 + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1 Filter Operator predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2 + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2 Stage: Stage-9 Conditional Operator @@ -2836,11 +2948,15 @@ STAGE PLANS: Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE @@ -2852,13 +2968,17 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE @@ -2867,12 +2987,16 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Dependency Collection @@ -2949,11 +3073,15 @@ STAGE PLANS: Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE @@ -2965,13 +3093,17 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE @@ -2980,12 +3112,16 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Dependency Collection @@ -3062,11 +3198,15 @@ STAGE PLANS: Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE @@ -3078,13 +3218,17 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE @@ -3093,12 +3237,16 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Dependency Collection @@ -3175,11 +3323,15 @@ STAGE PLANS: Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE @@ -3191,13 +3343,17 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE @@ -3206,12 +3362,16 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Dependency Collection @@ -3326,11 +3486,15 @@ STAGE PLANS: Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE @@ -3342,13 +3506,17 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE @@ -3357,12 +3525,16 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-6 Dependency Collection @@ -3550,11 +3722,15 @@ STAGE PLANS: Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE @@ -3566,13 +3742,17 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE @@ -3581,12 +3761,16 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-6 Dependency Collection @@ -3784,11 +3968,15 @@ STAGE PLANS: Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE @@ -3800,13 +3988,17 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE @@ -3815,12 +4007,16 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-11 Conditional Operator @@ -4096,11 +4292,15 @@ STAGE PLANS: Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE @@ -4112,13 +4312,17 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE @@ -4127,12 +4331,16 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-11 Conditional Operator diff --git a/ql/src/test/results/clientpositive/multi_insert_union_src.q.out b/ql/src/test/results/clientpositive/multi_insert_union_src.q.out index 3a35323..bd2521e 100644 --- a/ql/src/test/results/clientpositive/multi_insert_union_src.q.out +++ b/ql/src/test/results/clientpositive/multi_insert_union_src.q.out @@ -73,20 +73,28 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 150) (type: boolean) Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Filter Operator predicate: (_col0 > 400) (type: boolean) Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -102,20 +110,28 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 150) (type: boolean) Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Filter Operator predicate: (_col0 > 400) (type: boolean) Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) diff --git a/ql/src/test/results/clientpositive/multi_join_union.q.out b/ql/src/test/results/clientpositive/multi_join_union.q.out index 466f34b..74cf873 100644 --- a/ql/src/test/results/clientpositive/multi_join_union.q.out +++ b/ql/src/test/results/clientpositive/multi_join_union.q.out @@ -95,10 +95,14 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col6 (type: string) - 1 _col1 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 _col6 (type: string) + 1 _col1 (type: string) c-subquery2:a-subquery2:src14 TableScan alias: src14 @@ -112,10 +116,14 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col6 (type: string) - 1 _col1 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 _col6 (type: string) + 1 _col1 (type: string) Stage: Stage-5 Map Reduce diff --git a/ql/src/test/results/clientpositive/noalias_subq1.q.out b/ql/src/test/results/clientpositive/noalias_subq1.q.out index 91c0138..11545c0 100644 --- a/ql/src/test/results/clientpositive/noalias_subq1.q.out +++ b/ql/src/test/results/clientpositive/noalias_subq1.q.out @@ -13,14 +13,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: x:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: c1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out b/ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out index feadd5a..bc8fa0b 100644 --- a/ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out +++ b/ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out @@ -17,11 +17,11 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) + 1.0) (type: double), ((UDFToDouble(key) + 1.0) + 1.0) (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: nkey, _o__c1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -37,7 +37,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[9][tables = [tmp4:tmp2:tmp1:src1, ]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- This test query is introduced for HIVE-4968. -- First, we do not convert the join to MapJoin. EXPLAIN @@ -72,10 +72,10 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: tmp4:tmp3:src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -89,7 +89,7 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -102,21 +102,21 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: tmp4:tmp2:tmp1:src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) + value expressions: key (type: string), value (type: string) TableScan Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + value expressions: $f0 (type: bigint) Reduce Operator Tree: Join Operator condition map: @@ -124,15 +124,19 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, $f0 Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), $f0 (type: bigint) + outputColumnNames: key, value, $f0 Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -140,7 +144,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[9][tables = [tmp4:tmp2:tmp1:src1, ]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count FROM (SELECT * @@ -188,7 +192,7 @@ POSTHOOK: Input: default@src1 406 val_406 25 66 val_66 25 98 val_98 25 -Warning: Map Join MAPJOIN[18][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +Warning: Map Join MAPJOIN[14][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: -- Then, we convert the join to MapJoin. EXPLAIN SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count @@ -222,10 +226,10 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: tmp4:tmp3:src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -239,7 +243,7 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -251,17 +255,17 @@ STAGE PLANS: Stage: Stage-4 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:src1 + tmp4:tmp2:tmp1:src1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:src1 + tmp4:tmp2:tmp1:src1 TableScan - alias: src1 + alias: tmp4:tmp2:tmp1:src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: @@ -278,15 +282,19 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, $f0 Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), $f0 (type: bigint) + outputColumnNames: key, value, $f0 Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -296,7 +304,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[18][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +Warning: Map Join MAPJOIN[14][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count FROM (SELECT * diff --git a/ql/src/test/results/clientpositive/nonmr_fetch.q.out b/ql/src/test/results/clientpositive/nonmr_fetch.q.out index a4ce905..16340c3 100644 --- a/ql/src/test/results/clientpositive/nonmr_fetch.q.out +++ b/ql/src/test/results/clientpositive/nonmr_fetch.q.out @@ -17,7 +17,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -59,7 +59,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), '11' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -103,7 +103,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -150,7 +150,7 @@ STAGE PLANS: Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -258,7 +258,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -300,7 +300,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), '11' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -346,7 +346,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToInteger(key) * 10) (type: int), upper(value) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _o__c0, _o__c1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -393,7 +393,7 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -437,7 +437,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -486,7 +486,7 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, BLOCK__OFFSET__INSIDE__FILE Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -533,7 +533,7 @@ STAGE PLANS: Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: key, value, ds, hr, BLOCK__OFFSET__INSIDE__FILE Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 30 @@ -790,14 +790,14 @@ STAGE PLANS: limit: 20 Processor Tree: TableScan - alias: src + alias: a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 200.0) and (UDFToDouble(key) < 250.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 @@ -933,25 +933,33 @@ STAGE PLANS: Processor Tree: TableScan alias: srcpart - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (rand() > 1.0) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) - outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) + outputColumnNames: key, value, ds, BLOCK__OFFSET__INSIDE__FILE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ds = '2008-04-09') and (rand() > 1.0)) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - ListSink + Select Operator + expressions: key (type: string), value (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) + outputColumnNames: key, value, block__offset__inside__file + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + ListSink PREHOOK: query: select key, value, BLOCK__OFFSET__INSIDE__FILE from srcpart where ds="2008-04-09" AND rand() > 1 PREHOOK: type: QUERY PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### POSTHOOK: query: select key, value, BLOCK__OFFSET__INSIDE__FILE from srcpart where ds="2008-04-09" AND rand() > 1 POSTHOOK: type: QUERY POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### @@ -974,11 +982,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -993,15 +1001,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1028,10 +1040,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1044,15 +1056,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1081,10 +1097,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1097,16 +1113,20 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcx + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcx Stage: Stage-0 Move Operator @@ -1169,46 +1189,50 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/nonmr_fetch_threshold.q.out b/ql/src/test/results/clientpositive/nonmr_fetch_threshold.q.out index 6bfc624..d24faef 100644 --- a/ql/src/test/results/clientpositive/nonmr_fetch_threshold.q.out +++ b/ql/src/test/results/clientpositive/nonmr_fetch_threshold.q.out @@ -15,7 +15,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), '11' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -39,7 +39,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToInteger(key) * 10) (type: int), upper(value) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _o__c0, _o__c1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -63,7 +63,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), '11' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -87,7 +87,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToInteger(key) * 10) (type: int), upper(value) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _o__c0, _o__c1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -113,7 +113,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: concat(key, value) (type: string) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink @@ -136,7 +136,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), '11' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -160,7 +160,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToInteger(key) * 10) (type: int), upper(value) (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _o__c0, _o__c1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -186,7 +186,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: concat(key, value) (type: string) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/nonreserved_keywords_insert_into1.q.out b/ql/src/test/results/clientpositive/nonreserved_keywords_insert_into1.q.out index e70673e..ba65d89 100644 --- a/ql/src/test/results/clientpositive/nonreserved_keywords_insert_into1.q.out +++ b/ql/src/test/results/clientpositive/nonreserved_keywords_insert_into1.q.out @@ -16,8 +16,13 @@ POSTHOOK: query: EXPLAIN INSERT INTO TABLE `insert` SELECT * FROM src LIMIT 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 @@ -28,35 +33,32 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: UDFToInteger(key) (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 100 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.insert + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -71,6 +73,36 @@ STAGE PLANS: Stage: Stage-2 Stats-Aggr Operator + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: INSERT INTO TABLE `insert` SELECT * FROM src LIMIT 100 PREHOOK: type: QUERY PREHOOK: Input: default@src @@ -100,8 +132,13 @@ POSTHOOK: query: EXPLAIN INSERT INTO TABLE `insert` SELECT * FROM src LIMIT 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 @@ -112,35 +149,32 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: UDFToInteger(key) (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 100 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.insert + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -155,6 +189,36 @@ STAGE PLANS: Stage: Stage-2 Stats-Aggr Operator + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: INSERT INTO TABLE `insert` SELECT * FROM src LIMIT 100 PREHOOK: type: QUERY PREHOOK: Input: default@src @@ -193,8 +257,13 @@ POSTHOOK: query: EXPLAIN INSERT OVERWRITE TABLE `insert` SELECT * FROM src LIMIT POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 @@ -205,35 +274,32 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: UDFToInteger(key) (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.insert + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -248,6 +314,36 @@ STAGE PLANS: Stage: Stage-2 Stats-Aggr Operator + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: INSERT OVERWRITE TABLE `insert` SELECT * FROM src LIMIT 10 PREHOOK: type: QUERY PREHOOK: Input: default@src diff --git a/ql/src/test/results/clientpositive/notable_alias1.q.out b/ql/src/test/results/clientpositive/notable_alias1.q.out index 200b31c..b82add9 100644 --- a/ql/src/test/results/clientpositive/notable_alias1.q.out +++ b/ql/src/test/results/clientpositive/notable_alias1.q.out @@ -30,12 +30,12 @@ STAGE PLANS: predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -50,10 +50,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '1234' (type: string), UDFToInteger(_col0) (type: int), UDFToDouble(_col1) (type: double) + expressions: '1234' (type: string), UDFToInteger($f0) (type: int), UDFToDouble($f1) (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/notable_alias2.q.out b/ql/src/test/results/clientpositive/notable_alias2.q.out index 4df8073..3a11d98 100644 --- a/ql/src/test/results/clientpositive/notable_alias2.q.out +++ b/ql/src/test/results/clientpositive/notable_alias2.q.out @@ -30,12 +30,12 @@ STAGE PLANS: predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -50,10 +50,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '1234' (type: string), UDFToInteger(_col0) (type: int), UDFToDouble(_col1) (type: double) + expressions: '1234' (type: string), UDFToInteger($f0) (type: int), UDFToDouble($f1) (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/nullformatCTAS.q.out b/ql/src/test/results/clientpositive/nullformatCTAS.q.out index 7adca68..2ca5be6 100644 --- a/ql/src/test/results/clientpositive/nullformatCTAS.q.out +++ b/ql/src/test/results/clientpositive/nullformatCTAS.q.out @@ -64,7 +64,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 130 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: a, b Statistics: Num rows: 1 Data size: 130 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/nullgroup.q.out b/ql/src/test/results/clientpositive/nullgroup.q.out index 33fde55..cc55168 100644 --- a/ql/src/test/results/clientpositive/nullgroup.q.out +++ b/ql/src/test/results/clientpositive/nullgroup.q.out @@ -19,9 +19,11 @@ STAGE PLANS: predicate: (UDFToDouble(key) > 9999.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -33,15 +35,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: final - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -79,9 +85,11 @@ STAGE PLANS: predicate: (UDFToDouble(key) > 9999.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -93,15 +101,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -140,14 +152,17 @@ STAGE PLANS: predicate: (UDFToDouble(key) > 9999.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: $f0 (type: int) Reduce Operator Tree: Group By Operator - aggregations: count(1) + aggregations: count(VALUE._col0) mode: partial1 outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -170,15 +185,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: final - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -216,23 +235,30 @@ STAGE PLANS: predicate: (UDFToDouble(key) > 9999.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: $f0 (type: int) Reduce Operator Tree: Group By Operator - aggregations: count(1) + aggregations: count(VALUE._col0) mode: complete - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/nullgroup2.q.out b/ql/src/test/results/clientpositive/nullgroup2.q.out index 699068c..bfdab07 100644 --- a/ql/src/test/results/clientpositive/nullgroup2.q.out +++ b/ql/src/test/results/clientpositive/nullgroup2.q.out @@ -20,12 +20,12 @@ STAGE PLANS: predicate: (UDFToDouble(key) > 9999.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -64,15 +64,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -109,12 +113,12 @@ STAGE PLANS: predicate: (UDFToDouble(key) > 9999.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -129,15 +133,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -175,17 +183,18 @@ STAGE PLANS: predicate: (UDFToDouble(key) > 9999.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: int) Reduce Operator Tree: Group By Operator - aggregations: count(1) + aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0, _col1 @@ -212,15 +221,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -257,28 +270,33 @@ STAGE PLANS: predicate: (UDFToDouble(key) > 9999.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: $f0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: int) Reduce Operator Tree: Group By Operator - aggregations: count(1) + aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: complete - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/nullgroup3.q.out b/ql/src/test/results/clientpositive/nullgroup3.q.out index edce68c..d2c53a4 100644 --- a/ql/src/test/results/clientpositive/nullgroup3.q.out +++ b/ql/src/test/results/clientpositive/nullgroup3.q.out @@ -42,9 +42,11 @@ STAGE PLANS: alias: tstparttbl Statistics: Num rows: 1 Data size: 5812 Basic stats: PARTIAL Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 5812 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -56,15 +58,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -129,9 +135,11 @@ STAGE PLANS: alias: tstparttbl2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -143,15 +151,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -224,9 +236,11 @@ STAGE PLANS: alias: tstparttbl Statistics: Num rows: 1 Data size: 5812 Basic stats: PARTIAL Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 5812 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -238,15 +252,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -319,9 +337,11 @@ STAGE PLANS: alias: tstparttbl2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -333,15 +353,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/nullgroup4.q.out b/ql/src/test/results/clientpositive/nullgroup4.q.out index 8d7e5ee..8997557 100644 --- a/ql/src/test/results/clientpositive/nullgroup4.q.out +++ b/ql/src/test/results/clientpositive/nullgroup4.q.out @@ -20,12 +20,12 @@ STAGE PLANS: predicate: (UDFToDouble(key) = 9999.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col1 + expressions: 1 (type: int), value (type: string) + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), count(DISTINCT _col1) - keys: _col1 (type: string) + aggregations: count($f0), count(DISTINCT $f1) + keys: $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -60,15 +60,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0), count(VALUE._col1) mode: final - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -106,12 +110,12 @@ STAGE PLANS: predicate: (UDFToDouble(key) = 9999.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col1 + expressions: 1 (type: int), value (type: string) + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), count(DISTINCT _col1) - keys: _col1 (type: string) + aggregations: count($f0), count(DISTINCT $f1) + keys: $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -124,15 +128,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0), count(DISTINCT KEY._col0:0._col0) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -172,16 +180,16 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: $f1 (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: $f1 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - aggregations: count(1), count(DISTINCT KEY._col0:0._col0) + aggregations: count(KEY._col0:0._col0), count(DISTINCT KEY._col0:0._col0) mode: partial1 outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -204,15 +212,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0), count(VALUE._col1) mode: final - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -251,25 +263,29 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: $f1 (type: string) sort order: + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - aggregations: count(1), count(DISTINCT KEY._col0:0._col0) + aggregations: count(KEY._col0:0._col0), count(DISTINCT KEY._col0:0._col0) mode: complete - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out b/ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out index e85cceb..3efc8e5 100644 --- a/ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out @@ -19,12 +19,12 @@ STAGE PLANS: predicate: (UDFToDouble(key) = 9999.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), substr(value, 5) (type: string) - outputColumnNames: _col1, _col2 + expressions: 1 (type: int), value (type: string), substr(value, 5) (type: string) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), count(DISTINCT _col1), count(DISTINCT _col2) - keys: _col1 (type: string), _col2 (type: string) + aggregations: count($f0), count(DISTINCT $f1), count(DISTINCT $f2) + keys: $f1 (type: string), $f2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -37,15 +37,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -84,25 +88,29 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), substr(value, 5) (type: string) - outputColumnNames: _col1, _col2 + outputColumnNames: $f1, $f2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string), _col2 (type: string) + key expressions: $f1 (type: string), $f2 (type: string) sort order: ++ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - aggregations: count(1), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0) + aggregations: count(KEY._col0:0._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0) mode: complete - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/nullgroup5.q.out b/ql/src/test/results/clientpositive/nullgroup5.q.out index ef4d185..7612600 100644 --- a/ql/src/test/results/clientpositive/nullgroup5.q.out +++ b/ql/src/test/results/clientpositive/nullgroup5.q.out @@ -57,40 +57,48 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: null-subquery1:u-subquery1:x Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (ds = '2009-04-05') (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 30 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 30 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 30 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: y + alias: null-subquery2:u-subquery2:y Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 30 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 30 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 30 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/num_op_type_conv.q.out b/ql/src/test/results/clientpositive/num_op_type_conv.q.out index 013a153..61ff6b3 100644 --- a/ql/src/test/results/clientpositive/num_op_type_conv.q.out +++ b/ql/src/test/results/clientpositive/num_op_type_conv.q.out @@ -21,7 +21,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: null (type: double), null (type: double), null (type: double), 1 (type: bigint), 0 (type: bigint), 0.0 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5 Statistics: Num rows: 500 Data size: 12000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 diff --git a/ql/src/test/results/clientpositive/optimize_nullscan.q.out b/ql/src/test/results/clientpositive/optimize_nullscan.q.out index 386dd6b..b9d2733 100644 --- a/ql/src/test/results/clientpositive/optimize_nullscan.q.out +++ b/ql/src/test/results/clientpositive/optimize_nullscan.q.out @@ -185,20 +185,24 @@ STAGE PLANS: isSamplingPred: false predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: count(key) - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: count(key) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - tag: -1 - value expressions: _col1 (type: bigint) - auto parallelism: false + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + tag: -1 + value expressions: _col1 (type: bigint) + auto parallelism: false Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -665,27 +669,31 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1 - columns.types string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1 + columns.types string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -783,17 +791,21 @@ STAGE PLANS: isSamplingPred: false predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(key) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(key) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: -mr-10004default.src{} [null-subquery1:_u1-subquery1:src] Path -> Partition: @@ -849,23 +861,27 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -874,52 +890,60 @@ STAGE PLANS: GatherStats: false Union Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false TableScan GatherStats: false Union Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1187,23 +1211,27 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -1639,27 +1667,31 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1 - columns.types string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1 + columns.types string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -1848,23 +1880,27 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0 - columns.types string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0 + columns.types string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -1883,52 +1919,60 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false TableScan GatherStats: false Union Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Path -> Alias: -mr-10003default.src{} [null-subquery1:a-subquery1:src] #### A masked pattern was here #### @@ -2238,17 +2282,19 @@ STAGE PLANS: isSamplingPred: false predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: -mr-10002default.src{} [src] Path -> Partition: @@ -2304,27 +2350,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/optional_outer.q.out b/ql/src/test/results/clientpositive/optional_outer.q.out index c1256f6..5544b63 100644 --- a/ql/src/test/results/clientpositive/optional_outer.q.out +++ b/ql/src/test/results/clientpositive/optional_outer.q.out @@ -15,43 +15,47 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -76,43 +80,47 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -137,43 +145,47 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -198,43 +210,47 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -259,43 +275,47 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -320,43 +340,47 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/orc_analyze.q.out b/ql/src/test/results/clientpositive/orc_analyze.q.out index 6eb9a93..bc46852 100644 --- a/ql/src/test/results/clientpositive/orc_analyze.q.out +++ b/ql/src/test/results/clientpositive/orc_analyze.q.out @@ -106,7 +106,7 @@ Table Parameters: numFiles 1 numRows 100 rawDataSize 52600 - totalSize 3174 + totalSize 3202 #### A masked pattern was here #### # Storage Information @@ -154,7 +154,7 @@ Table Parameters: numFiles 1 numRows 100 rawDataSize 52600 - totalSize 3174 + totalSize 3202 #### A masked pattern was here #### # Storage Information @@ -202,7 +202,7 @@ Table Parameters: numFiles 1 numRows 100 rawDataSize 52600 - totalSize 3174 + totalSize 3202 #### A masked pattern was here #### # Storage Information @@ -291,7 +291,7 @@ Table Parameters: numFiles 1 numRows 100 rawDataSize 52600 - totalSize 3174 + totalSize 3202 #### A masked pattern was here #### # Storage Information @@ -405,7 +405,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 21950 - totalSize 2073 + totalSize 2102 #### A masked pattern was here #### # Storage Information @@ -448,7 +448,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 22050 - totalSize 2088 + totalSize 2118 #### A masked pattern was here #### # Storage Information @@ -503,7 +503,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 21950 - totalSize 2073 + totalSize 2102 #### A masked pattern was here #### # Storage Information @@ -546,7 +546,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 22050 - totalSize 2088 + totalSize 2118 #### A masked pattern was here #### # Storage Information @@ -601,7 +601,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 21950 - totalSize 2073 + totalSize 2102 #### A masked pattern was here #### # Storage Information @@ -644,7 +644,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 22050 - totalSize 2088 + totalSize 2118 #### A masked pattern was here #### # Storage Information @@ -744,7 +744,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 21950 - totalSize 2073 + totalSize 2102 #### A masked pattern was here #### # Storage Information @@ -787,7 +787,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 22050 - totalSize 2088 + totalSize 2118 #### A masked pattern was here #### # Storage Information @@ -907,7 +907,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 21950 - totalSize 2073 + totalSize 2102 #### A masked pattern was here #### # Storage Information @@ -950,7 +950,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 22050 - totalSize 2088 + totalSize 2118 #### A masked pattern was here #### # Storage Information @@ -1005,7 +1005,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 21950 - totalSize 2073 + totalSize 2102 #### A masked pattern was here #### # Storage Information @@ -1048,7 +1048,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 22050 - totalSize 2088 + totalSize 2118 #### A masked pattern was here #### # Storage Information @@ -1103,7 +1103,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 21950 - totalSize 2073 + totalSize 2102 #### A masked pattern was here #### # Storage Information @@ -1146,7 +1146,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 22050 - totalSize 2088 + totalSize 2118 #### A masked pattern was here #### # Storage Information @@ -1252,7 +1252,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 21950 - totalSize 2073 + totalSize 2102 #### A masked pattern was here #### # Storage Information @@ -1295,7 +1295,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 22050 - totalSize 2088 + totalSize 2118 #### A masked pattern was here #### # Storage Information @@ -1460,7 +1460,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 21950 - totalSize 2073 + totalSize 2102 #### A masked pattern was here #### # Storage Information @@ -1560,7 +1560,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 21950 - totalSize 2073 + totalSize 2102 #### A masked pattern was here #### # Storage Information @@ -1660,7 +1660,7 @@ Partition Parameters: numFiles 1 numRows 50 rawDataSize 21950 - totalSize 2073 + totalSize 2102 #### A masked pattern was here #### # Storage Information diff --git a/ql/src/test/results/clientpositive/orc_createas1.q.out b/ql/src/test/results/clientpositive/orc_createas1.q.out index f5a23db..aa8fd2e 100644 --- a/ql/src/test/results/clientpositive/orc_createas1.q.out +++ b/ql/src/test/results/clientpositive/orc_createas1.q.out @@ -72,7 +72,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -161,17 +161,17 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 @@ -235,7 +235,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), (hash(key) pmod 50) (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, part Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/orc_dictionary_threshold.q.out b/ql/src/test/results/clientpositive/orc_dictionary_threshold.q.out index a57243e..2aca9fb 100644 --- a/ql/src/test/results/clientpositive/orc_dictionary_threshold.q.out +++ b/ql/src/test/results/clientpositive/orc_dictionary_threshold.q.out @@ -149,7 +149,7 @@ SELECT CONCAT("k", key) AS key FROM src_thousand POSTHOOK: type: QUERY POSTHOOK: Input: default@src_thousand POSTHOOK: Output: default@test_orc -POSTHOOK: Lineage: test_orc.key EXPRESSION [(src_thousand)src_thousand.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: test_orc.key EXPRESSION [(src_thousand)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1:a-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1:src_thousand.FieldSchema(name:key, type:string, comment:null), (src_thousand)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:a-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src_thousand.FieldSchema(name:key, type:string, comment:null), (src_thousand)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:a-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src_thousand.FieldSchema(name:key, type:string, comment:null), (src_thousand)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:a-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src_thousand.FieldSchema(name:key, type:string, comment:null), (src_thousand)null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:a-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src_thousand.FieldSchema(name:key, type:string, comment:null), (src_thousand)null-subquery2:a-subquery2:src_thousand.FieldSchema(name:key, type:string, comment:null), ] PREHOOK: query: SELECT SUM(HASH(key)) FROM test_orc PREHOOK: type: QUERY PREHOOK: Input: default@test_orc diff --git a/ql/src/test/results/clientpositive/orc_file_dump.q.out b/ql/src/test/results/clientpositive/orc_file_dump.q.out index 67aa189..32c41d3 100644 --- a/ql/src/test/results/clientpositive/orc_file_dump.q.out +++ b/ql/src/test/results/clientpositive/orc_file_dump.q.out @@ -97,7 +97,7 @@ File Version: 0.12 with HIVE_8732 Rows: 1049 Compression: ZLIB Compression size: 262144 -Type: struct<_col0:tinyint,_col1:smallint,_col2:int,_col3:bigint,_col4:float,_col5:double,_col6:boolean,_col7:string,_col8:timestamp,_col9:decimal(4,2),_col10:binary> +Type: struct Stripe Statistics: Stripe 1: @@ -192,7 +192,7 @@ Stripes: Entry 1: numHashFunctions: 4 bitCount: 6272 popCount: 168 loadFactor: 0.0268 expectedFpp: 5.147697E-7 Stripe level merge: numHashFunctions: 4 bitCount: 6272 popCount: 492 loadFactor: 0.0784 expectedFpp: 3.7864847E-5 -File length: 33456 bytes +File length: 33458 bytes Padding length: 0 bytes Padding ratio: 0% -- END ORC FILE DUMP -- @@ -215,7 +215,7 @@ File Version: 0.12 with HIVE_8732 Rows: 1049 Compression: ZLIB Compression size: 262144 -Type: struct<_col0:tinyint,_col1:smallint,_col2:int,_col3:bigint,_col4:float,_col5:double,_col6:boolean,_col7:string,_col8:timestamp,_col9:decimal(4,2),_col10:binary> +Type: struct Stripe Statistics: Stripe 1: @@ -310,7 +310,7 @@ Stripes: Entry 1: numHashFunctions: 7 bitCount: 9600 popCount: 285 loadFactor: 0.0297 expectedFpp: 2.0324289E-11 Stripe level merge: numHashFunctions: 7 bitCount: 9600 popCount: 849 loadFactor: 0.0884 expectedFpp: 4.231118E-8 -File length: 38610 bytes +File length: 38613 bytes Padding length: 0 bytes Padding ratio: 0% -- END ORC FILE DUMP -- @@ -345,7 +345,7 @@ File Version: 0.12 with HIVE_8732 Rows: 1049 Compression: ZLIB Compression size: 262144 -Type: struct<_col0:tinyint,_col1:smallint,_col2:int,_col3:bigint,_col4:float,_col5:double,_col6:boolean,_col7:string,_col8:timestamp,_col9:decimal(4,2),_col10:binary> +Type: struct Stripe Statistics: Stripe 1: @@ -440,7 +440,7 @@ Stripes: Entry 1: numHashFunctions: 4 bitCount: 6272 popCount: 168 loadFactor: 0.0268 expectedFpp: 5.147697E-7 Stripe level merge: numHashFunctions: 4 bitCount: 6272 popCount: 492 loadFactor: 0.0784 expectedFpp: 3.7864847E-5 -File length: 33456 bytes +File length: 33458 bytes Padding length: 0 bytes Padding ratio: 0% -- END ORC FILE DUMP -- diff --git a/ql/src/test/results/clientpositive/orc_int_type_promotion.q.out b/ql/src/test/results/clientpositive/orc_int_type_promotion.q.out index d26dff2..25fcc54 100644 --- a/ql/src/test/results/clientpositive/orc_int_type_promotion.q.out +++ b/ql/src/test/results/clientpositive/orc_int_type_promotion.q.out @@ -220,14 +220,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypes_orc - Statistics: Num rows: 88 Data size: 1772 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 88 Data size: 1766 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ti (type: tinyint), si (type: smallint), i (type: int), bi (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 88 Data size: 1772 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: ti, si, i, bi + Statistics: Num rows: 88 Data size: 1766 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 88 Data size: 1772 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 88 Data size: 1766 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/orc_merge3.q.out b/ql/src/test/results/clientpositive/orc_merge3.q.out index 7bf12c6..37ce936 100644 --- a/ql/src/test/results/clientpositive/orc_merge3.q.out +++ b/ql/src/test/results/clientpositive/orc_merge3.q.out @@ -73,7 +73,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/orc_merge4.q.out b/ql/src/test/results/clientpositive/orc_merge4.q.out index 828f204..5b471c2 100644 --- a/ql/src/test/results/clientpositive/orc_merge4.q.out +++ b/ql/src/test/results/clientpositive/orc_merge4.q.out @@ -91,7 +91,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 94000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1000 Data size: 94000 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/orc_merge5.q.out b/ql/src/test/results/clientpositive/orc_merge5.q.out index 77c01c7..69134a5 100644 --- a/ql/src/test/results/clientpositive/orc_merge5.q.out +++ b/ql/src/test/results/clientpositive/orc_merge5.q.out @@ -50,7 +50,7 @@ STAGE PLANS: Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: userid (type: bigint), string1 (type: string), subtype (type: double), decimal1 (type: decimal(10,0)), ts (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: userid, string1, subtype, decimal1, ts Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -139,7 +139,7 @@ STAGE PLANS: Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: userid (type: bigint), string1 (type: string), subtype (type: double), decimal1 (type: decimal(10,0)), ts (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: userid, string1, subtype, decimal1, ts Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/orc_merge6.q.out b/ql/src/test/results/clientpositive/orc_merge6.q.out index 05f548c..58565f2 100644 --- a/ql/src/test/results/clientpositive/orc_merge6.q.out +++ b/ql/src/test/results/clientpositive/orc_merge6.q.out @@ -52,7 +52,7 @@ STAGE PLANS: Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: userid (type: bigint), string1 (type: string), subtype (type: double), decimal1 (type: decimal(10,0)), ts (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: userid, string1, subtype, decimal1, ts Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -186,7 +186,7 @@ STAGE PLANS: Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: userid (type: bigint), string1 (type: string), subtype (type: double), decimal1 (type: decimal(10,0)), ts (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: userid, string1, subtype, decimal1, ts Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/orc_merge_incompat1.q.out b/ql/src/test/results/clientpositive/orc_merge_incompat1.q.out index 7a9c772..4db6306 100644 --- a/ql/src/test/results/clientpositive/orc_merge_incompat1.q.out +++ b/ql/src/test/results/clientpositive/orc_merge_incompat1.q.out @@ -49,7 +49,7 @@ STAGE PLANS: Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: userid (type: bigint), string1 (type: string), subtype (type: double), decimal1 (type: decimal(10,0)), ts (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: userid, string1, subtype, decimal1, ts Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/orc_predicate_pushdown.q.out b/ql/src/test/results/clientpositive/orc_predicate_pushdown.q.out index 0d4cd15..5c14b86 100644 --- a/ql/src/test/results/clientpositive/orc_predicate_pushdown.q.out +++ b/ql/src/test/results/clientpositive/orc_predicate_pushdown.q.out @@ -138,10 +138,10 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hash(t) (type: int) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -153,15 +153,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -186,10 +190,10 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hash(t) (type: int) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -201,15 +205,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -317,10 +325,10 @@ STAGE PLANS: Statistics: Num rows: 116 Data size: 34409 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hash(t) (type: int) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 116 Data size: 34409 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -332,15 +340,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -375,10 +387,10 @@ STAGE PLANS: Statistics: Num rows: 116 Data size: 34409 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hash(t) (type: int) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 116 Data size: 34409 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -390,15 +402,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -772,17 +788,17 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 1186 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: t, si, d, s Statistics: Num rows: 4 Data size: 1186 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: s (type: string) sort order: - Statistics: Num rows: 4 Data size: 1186 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: double) + value expressions: t (type: tinyint), si (type: smallint), d (type: double) Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: double), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: VALUE.t (type: tinyint), VALUE.si (type: smallint), VALUE.d (type: double), KEY.reducesinkkey0 (type: string) + outputColumnNames: t, si, d, s Statistics: Num rows: 4 Data size: 1186 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 3 @@ -840,17 +856,17 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 1186 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: t, si, d, s Statistics: Num rows: 4 Data size: 1186 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: s (type: string) sort order: - Statistics: Num rows: 4 Data size: 1186 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: double) + value expressions: t (type: tinyint), si (type: smallint), d (type: double) Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: double), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: VALUE.t (type: tinyint), VALUE.si (type: smallint), VALUE.d (type: double), KEY.reducesinkkey0 (type: string) + outputColumnNames: t, si, d, s Statistics: Num rows: 4 Data size: 1186 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 3 diff --git a/ql/src/test/results/clientpositive/order.q.out b/ql/src/test/results/clientpositive/order.q.out index 13eee2e..a530027 100644 --- a/ql/src/test/results/clientpositive/order.q.out +++ b/ql/src/test/results/clientpositive/order.q.out @@ -17,17 +17,17 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -83,17 +83,17 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 diff --git a/ql/src/test/results/clientpositive/order2.q.out b/ql/src/test/results/clientpositive/order2.q.out index 3a38b46..d069835 100644 --- a/ql/src/test/results/clientpositive/order2.q.out +++ b/ql/src/test/results/clientpositive/order2.q.out @@ -17,39 +17,43 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: x + alias: subq:x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(_col0) < 10.0) (type: boolean) + predicate: (UDFToDouble(key) < 10.0) (type: boolean) Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator - limit: -1 + limit: 10 Processor Tree: ListSink diff --git a/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.7.out b/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.7.out index bfe983a..c19b47a 100644 --- a/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.7.out +++ b/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.7.out @@ -120,15 +120,15 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false TableScan alias: b @@ -136,15 +136,15 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string), _col2 (type: string) + value expressions: value (type: string), ds (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -378,11 +378,11 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b] - /srcpart/ds=2008-04-09/hr=11 [$hdt$_1:b] - /srcpart/ds=2008-04-09/hr=12 [$hdt$_1:b] + /src [a] + /srcpart/ds=2008-04-08/hr=11 [b] + /srcpart/ds=2008-04-08/hr=12 [b] + /srcpart/ds=2008-04-09/hr=11 [b] + /srcpart/ds=2008-04-09/hr=12 [b] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -392,37 +392,41 @@ STAGE PLANS: 1 [0, 1] filter predicates: 0 - 1 {(VALUE._col1 = '2008-04-08')} + 1 {(VALUE.ds = '2008-04-08')} keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) and (UDFToDouble(_col2) > 15.0)) and (UDFToDouble(_col2) < 25.0)) (type: boolean) + predicate: ((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key0) > 15.0)) and (UDFToDouble(key0) < 25.0)) (type: boolean) Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns key,value,key0,value0 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -592,15 +596,15 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false TableScan alias: b @@ -612,15 +616,15 @@ STAGE PLANS: Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -762,44 +766,48 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b] + /src [a] + /srcpart/ds=2008-04-08/hr=11 [b] + /srcpart/ds=2008-04-08/hr=12 [b] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean) + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns key,value,key0,value0 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/parallel.q.out b/ql/src/test/results/clientpositive/parallel.q.out index 737ceda..f6c0f65 100644 --- a/ql/src/test/results/clientpositive/parallel.q.out +++ b/ql/src/test/results/clientpositive/parallel.q.out @@ -63,12 +63,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -87,27 +91,35 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_a + File Output Operator + compressed: false + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_a Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_b + File Output Operator + compressed: false + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_b Stage: Stage-0 Move Operator diff --git a/ql/src/test/results/clientpositive/parallel_join0.q.out b/ql/src/test/results/clientpositive/parallel_join0.q.out index 0f57a51..080ea8f 100644 --- a/ql/src/test/results/clientpositive/parallel_join0.q.out +++ b/ql/src/test/results/clientpositive/parallel_join0.q.out @@ -65,12 +65,16 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -116,7 +120,7 @@ SELECT src1.key as k1, src1.value as v1, (SELECT * FROM src WHERE src.key < 10) src2 SORT BY k1, v1, k2, v2 POSTHOOK: type: QUERY -{"STAGE PLANS":{"Stage-2":{"Map Reduce":{"Reduce Operator Tree:":{"Select Operator":{"expressions:":"KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)","outputColumnNames:":["_col0","_col1","_col2","_col3"],"children":{"File Output Operator":{"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","compressed:":"false","table:":{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"}}},"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE"}},"Map Operator Tree:":[{"TableScan":{"children":{"Reduce Output Operator":{"sort order:":"++++","Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","key expressions:":"_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)"}}}}]}},"Stage-1":{"Map Reduce":{"Reduce Operator Tree:":{"Join Operator":{"keys:":{},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"children":{"File Output Operator":{"compressed:":"false","table:":{"serde:":"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe","input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat"}}},"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","condition map:":[{"":"Inner Join 0 to 1"}]}},"Map Operator Tree:":[{"TableScan":{"alias:":"src","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","outputColumnNames:":["_col0","_col1"],"children":{"Reduce Output Operator":{"sort order:":"","value expressions:":"_col0 (type: string), _col1 (type: string)","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE"}},{"TableScan":{"alias:":"src","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","outputColumnNames:":["_col0","_col1"],"children":{"Reduce Output Operator":{"sort order:":"","value expressions:":"_col0 (type: string), _col1 (type: string)","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE"}}]}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{}}}}},"STAGE DEPENDENCIES":{"Stage-2":{"DEPENDENT STAGES":"Stage-1"},"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-0":{"DEPENDENT STAGES":"Stage-2"}}} +{"STAGE PLANS":{"Stage-2":{"Map Reduce":{"Reduce Operator Tree:":{"Select Operator":{"expressions:":"KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)","outputColumnNames:":["_col0","_col1","_col2","_col3"],"children":{"File Output Operator":{"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","compressed:":"false","table:":{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"}}},"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE"}},"Map Operator Tree:":[{"TableScan":{"children":{"Reduce Output Operator":{"sort order:":"++++","Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","key expressions:":"_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)"}}}}]}},"Stage-1":{"Map Reduce":{"Reduce Operator Tree:":{"Join Operator":{"keys:":{},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"children":{"Select Operator":{"expressions:":"_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)","outputColumnNames:":["_col0","_col1","_col2","_col3"],"children":{"File Output Operator":{"compressed:":"false","table:":{"serde:":"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe","input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat"}}},"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","condition map:":[{"":"Inner Join 0 to 1"}]}},"Map Operator Tree:":[{"TableScan":{"alias:":"src","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","outputColumnNames:":["_col0","_col1"],"children":{"Reduce Output Operator":{"sort order:":"","value expressions:":"_col0 (type: string), _col1 (type: string)","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE"}},{"TableScan":{"alias:":"src","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","outputColumnNames:":["_col0","_col1"],"children":{"Reduce Output Operator":{"sort order:":"","value expressions:":"_col0 (type: string), _col1 (type: string)","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE"}},"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE"}}]}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{}}}}},"STAGE DEPENDENCIES":{"Stage-2":{"DEPENDENT STAGES":"Stage-1"},"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-0":{"DEPENDENT STAGES":"Stage-2"}}} Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT src1.key as k1, src1.value as v1, src2.key as k2, src2.value as v2 FROM diff --git a/ql/src/test/results/clientpositive/parallel_join1.q.out b/ql/src/test/results/clientpositive/parallel_join1.q.out index 9ce2646..53d7631 100644 --- a/ql/src/test/results/clientpositive/parallel_join1.q.out +++ b/ql/src/test/results/clientpositive/parallel_join1.q.out @@ -28,21 +28,21 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -51,24 +51,24 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col2) (type: int), _col1 (type: string) + expressions: UDFToInteger(key0) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -104,7 +104,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest_j1 POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest_j1.* FROM dest_j1 PREHOOK: type: QUERY PREHOOK: Input: default@dest_j1 diff --git a/ql/src/test/results/clientpositive/parquet_ctas.q.out b/ql/src/test/results/clientpositive/parquet_ctas.q.out index 68f0ead..d7ceeb3 100644 --- a/ql/src/test/results/clientpositive/parquet_ctas.q.out +++ b/ql/src/test/results/clientpositive/parquet_ctas.q.out @@ -88,8 +88,8 @@ PREHOOK: Input: default@parquet_ctas_advanced POSTHOOK: query: describe parquet_ctas_advanced POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@parquet_ctas_advanced -c0 int -c1 string +_o__c0 int +_o__c1 string PREHOOK: query: select * from parquet_ctas_advanced PREHOOK: type: QUERY PREHOOK: Input: default@parquet_ctas_advanced @@ -161,7 +161,7 @@ POSTHOOK: query: describe parquet_ctas_mixed POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@parquet_ctas_mixed key int -c1 int +_o__c1 int myvalue string PREHOOK: query: select * from parquet_ctas_mixed PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/parquet_predicate_pushdown.q.out b/ql/src/test/results/clientpositive/parquet_predicate_pushdown.q.out index aa3b272..3e9c718 100644 --- a/ql/src/test/results/clientpositive/parquet_predicate_pushdown.q.out +++ b/ql/src/test/results/clientpositive/parquet_predicate_pushdown.q.out @@ -128,10 +128,10 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 11539 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hash(t) (type: int) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1049 Data size: 11539 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -143,15 +143,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -176,10 +180,10 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 11539 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hash(t) (type: int) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1049 Data size: 11539 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -191,15 +195,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -327,7 +335,7 @@ STAGE PLANS: Statistics: Num rows: 116 Data size: 1276 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float), d (type: double), bo (type: boolean), s (type: string), ts (type: timestamp), dec (type: decimal(4,2)), bin (type: binary) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: t, si, i, b, f, d, bo, s, ts, dec, bin Statistics: Num rows: 116 Data size: 1276 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -375,7 +383,7 @@ STAGE PLANS: Statistics: Num rows: 116 Data size: 1276 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float), d (type: double), bo (type: boolean), s (type: string), ts (type: timestamp), dec (type: decimal(4,2)), bin (type: binary) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: t, si, i, b, f, d, bo, s, ts, dec, bin Statistics: Num rows: 116 Data size: 1276 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -760,17 +768,17 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 44 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: t, si, d, s Statistics: Num rows: 4 Data size: 44 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: s (type: string) sort order: - Statistics: Num rows: 4 Data size: 44 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: double) + value expressions: t (type: tinyint), si (type: smallint), d (type: double) Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: double), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: VALUE.t (type: tinyint), VALUE.si (type: smallint), VALUE.d (type: double), KEY.reducesinkkey0 (type: string) + outputColumnNames: t, si, d, s Statistics: Num rows: 4 Data size: 44 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 3 @@ -828,17 +836,17 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 44 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: t, si, d, s Statistics: Num rows: 4 Data size: 44 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: s (type: string) sort order: - Statistics: Num rows: 4 Data size: 44 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: double) + value expressions: t (type: tinyint), si (type: smallint), d (type: double) Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: double), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: VALUE.t (type: tinyint), VALUE.si (type: smallint), VALUE.d (type: double), KEY.reducesinkkey0 (type: string) + outputColumnNames: t, si, d, s Statistics: Num rows: 4 Data size: 44 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 3 diff --git a/ql/src/test/results/clientpositive/partition_boolexpr.q.out b/ql/src/test/results/clientpositive/partition_boolexpr.q.out index 05fe761..ec6fbe2 100644 --- a/ql/src/test/results/clientpositive/partition_boolexpr.q.out +++ b/ql/src/test/results/clientpositive/partition_boolexpr.q.out @@ -43,9 +43,11 @@ STAGE PLANS: alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -57,15 +59,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -91,28 +97,36 @@ STAGE PLANS: Filter Operator predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: count($f0) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -136,9 +150,11 @@ STAGE PLANS: alias: srcpart Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -150,15 +166,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -182,9 +202,11 @@ STAGE PLANS: alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -196,15 +218,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -228,9 +254,11 @@ STAGE PLANS: alias: srcpart Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -242,15 +270,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -276,28 +308,36 @@ STAGE PLANS: Filter Operator predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: count($f0) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/partition_multilevels.q.out b/ql/src/test/results/clientpositive/partition_multilevels.q.out index 31862e1..2d19255 100644 --- a/ql/src/test/results/clientpositive/partition_multilevels.q.out +++ b/ql/src/test/results/clientpositive/partition_multilevels.q.out @@ -991,11 +991,11 @@ STAGE PLANS: Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '2222' (type: string), level2 (type: string), level3 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: level1, level2, level3 Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) + keys: level1 (type: string), level2 (type: string), level3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE @@ -1010,15 +1010,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: level1, level2, level3, $f3 Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: level1 (type: string), level2 (type: string), level3 (type: string), $f3 (type: bigint) + outputColumnNames: level1, level2, level3, $f3 Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1579,11 +1583,11 @@ STAGE PLANS: Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '2222' (type: string), level2 (type: string), level3 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: level1, level2, level3 Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) + keys: level1 (type: string), level2 (type: string), level3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE @@ -1598,15 +1602,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: level1, level2, level3, $f3 Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: level1 (type: string), level2 (type: string), level3 (type: string), $f3 (type: bigint) + outputColumnNames: level1, level2, level3, $f3 Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out b/ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out index c8abc9e..17bf7a5 100644 --- a/ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out +++ b/ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out @@ -76,7 +76,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 58 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), dt (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, dt, BLOCK__OFFSET__INSIDE__FILE Statistics: Num rows: 8 Data size: 58 Basic stats: COMPLETE Column stats: NONE ListSink @@ -189,7 +189,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 58 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), dt (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, dt, BLOCK__OFFSET__INSIDE__FILE Statistics: Num rows: 8 Data size: 58 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/pcr.q.out b/ql/src/test/results/clientpositive/pcr.q.out index d7c40a3..df84b53 100644 --- a/ql/src/test/results/clientpositive/pcr.q.out +++ b/ql/src/test/results/clientpositive/pcr.q.out @@ -110,14 +110,14 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col2 (type: string) + key expressions: key (type: int), ds (type: string) sort order: ++ Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) + tag: 0 + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -218,8 +218,8 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: KEY.reducesinkkey0 (type: int), VALUE.value (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -232,7 +232,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2 + columns key,value,ds columns.types int:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -327,14 +327,14 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: key (type: int) sort order: + Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) + tag: 0 + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -481,8 +481,8 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: int), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -495,7 +495,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1 + columns key,value columns.types int:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -638,14 +638,14 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col2 (type: string) + key expressions: key (type: int), ds (type: string) sort order: ++ Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) + tag: 0 + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -746,8 +746,8 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: KEY.reducesinkkey0 (type: int), VALUE.value (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -760,7 +760,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2 + columns key,value,ds columns.types int:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -873,14 +873,14 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col2 (type: string) + key expressions: key (type: int), ds (type: string) sort order: ++ Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) + tag: 0 + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -981,8 +981,8 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: KEY.reducesinkkey0 (type: int), VALUE.value (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -995,7 +995,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2 + columns key,value,ds columns.types int:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -1110,14 +1110,14 @@ STAGE PLANS: Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col2 (type: string) + key expressions: key (type: int), ds (type: string) sort order: ++ Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) + tag: 0 + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -1264,8 +1264,8 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: KEY.reducesinkkey0 (type: int), VALUE.value (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1278,7 +1278,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2 + columns key,value,ds columns.types int:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -1403,14 +1403,14 @@ STAGE PLANS: Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col2 (type: string) + key expressions: key (type: int), ds (type: string) sort order: ++ Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) + tag: 0 + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -1557,8 +1557,8 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: KEY.reducesinkkey0 (type: int), VALUE.value (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1571,7 +1571,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2 + columns key,value,ds columns.types int:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -1696,13 +1696,13 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: 14 (type: int), _col1 (type: string) + key expressions: 14 (type: int), value (type: string) sort order: ++ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE - tag: -1 + tag: 0 auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -1804,7 +1804,7 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: 14 (type: int), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1817,7 +1817,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1 + columns key,value columns.types int:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -1901,13 +1901,13 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) + key expressions: key (type: int), value (type: string) sort order: ++ Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE - tag: -1 + tag: 0 auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -2009,7 +2009,7 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2022,7 +2022,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1 + columns key,value columns.types int:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -2146,13 +2146,13 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) + key expressions: key (type: int), value (type: string) sort order: ++ Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE - tag: -1 + tag: 0 auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -2300,7 +2300,7 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2313,7 +2313,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1 + columns key,value columns.types int:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -2479,13 +2479,13 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + key expressions: key (type: int), value (type: string), ds (type: string) sort order: +++ Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE - tag: -1 + tag: 0 auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -2587,7 +2587,7 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2600,7 +2600,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2 + columns key,value,ds columns.types int:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -3362,13 +3362,13 @@ STAGE PLANS: Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + key expressions: key (type: int), value (type: string), ds (type: string) sort order: +++ Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE - tag: -1 + tag: 0 auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -3562,7 +3562,7 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -3575,7 +3575,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2 + columns key,value,ds columns.types int:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -3725,13 +3725,13 @@ STAGE PLANS: Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + key expressions: key (type: int), value (type: string), ds (type: string) sort order: +++ Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE - tag: -1 + tag: 0 auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -3879,7 +3879,7 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -3892,7 +3892,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2 + columns key,value,ds columns.types int:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -5266,14 +5266,14 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) + tag: 0 + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -5329,8 +5329,8 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -5346,7 +5346,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1 + columns key,value columns.types string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -5448,15 +5448,15 @@ STAGE PLANS: predicate: (UDFToDouble(key) = 11.0) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), hr (type: string) - outputColumnNames: _col1, _col3 + expressions: hr (type: string), value (type: string) + outputColumnNames: hr, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: '11' (type: string), '2008-04-08' (type: string), _col3 (type: string) + key expressions: '11' (type: string), '2008-04-08' (type: string), hr (type: string) sort order: +++ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) + tag: 0 + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -5559,8 +5559,8 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: '11' (type: string), VALUE._col0 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: '11' (type: string), VALUE.value (type: string), '2008-04-08' (type: string), KEY.reducesinkkey2 (type: string) + outputColumnNames: key, value, ds, hr Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -5573,7 +5573,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2,_col3 + columns key,value,ds,hr columns.types string:string:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -5671,15 +5671,15 @@ STAGE PLANS: predicate: (UDFToDouble(key) = 11.0) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), ds (type: string) - outputColumnNames: _col1, _col2 + expressions: ds (type: string), value (type: string) + outputColumnNames: ds, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: '11' (type: string), _col2 (type: string), '11' (type: string) + key expressions: '11' (type: string), ds (type: string), '11' (type: string) sort order: +++ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) + tag: 0 + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -5782,8 +5782,8 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: '11' (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), '11' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: '11' (type: string), VALUE.value (type: string), KEY.reducesinkkey1 (type: string), '11' (type: string) + outputColumnNames: key, value, ds, hr Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -5796,7 +5796,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2,_col3 + columns key,value,ds,hr columns.types string:string:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -6084,7 +6084,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE ListSink @@ -6105,7 +6105,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE ListSink @@ -6126,7 +6126,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/plan_json.q.java1.7.out b/ql/src/test/results/clientpositive/plan_json.q.java1.7.out index 0979c70..f5ad5bd 100644 --- a/ql/src/test/results/clientpositive/plan_json.q.java1.7.out +++ b/ql/src/test/results/clientpositive/plan_json.q.java1.7.out @@ -10,4 +10,4 @@ POSTHOOK: query: -- explain plan json: the query gets the formatted json output EXPLAIN FORMATTED SELECT count(1) FROM src POSTHOOK: type: QUERY -{"STAGE PLANS":{"Stage-1":{"Map Reduce":{"Reduce Operator Tree:":{"Group By Operator":{"mode:":"mergepartial","aggregations:":["count(VALUE._col0)"],"outputColumnNames:":["_col0"],"children":{"File Output Operator":{"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","compressed:":"false","table:":{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"}}},"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE"}},"Map Operator Tree:":[{"TableScan":{"alias:":"src","children":{"Select Operator":{"children":{"Group By Operator":{"mode:":"hash","aggregations:":["count(1)"],"outputColumnNames:":["_col0"],"children":{"Reduce Output Operator":{"sort order:":"","value expressions:":"_col0 (type: bigint)","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE"}},"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE"}},"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE"}},"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE"}}]}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{}}}}},"STAGE DEPENDENCIES":{"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-0":{"DEPENDENT STAGES":"Stage-1"}}} +{"STAGE PLANS":{"Stage-1":{"Map Reduce":{"Reduce Operator Tree:":{"Group By Operator":{"mode:":"mergepartial","aggregations:":["count(VALUE._col0)"],"outputColumnNames:":["$f0"],"children":{"Select Operator":{"expressions:":"$f0 (type: bigint)","outputColumnNames:":["$f0"],"children":{"File Output Operator":{"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","compressed:":"false","table:":{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"}}},"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE"}},"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE"}},"Map Operator Tree:":[{"TableScan":{"alias:":"src","children":{"Select Operator":{"expressions:":"1 (type: int)","outputColumnNames:":["$f0"],"children":{"Group By Operator":{"mode:":"hash","aggregations:":["count($f0)"],"outputColumnNames:":["_col0"],"children":{"Reduce Output Operator":{"sort order:":"","value expressions:":"_col0 (type: bigint)","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE"}},"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE"}},"Statistics:":"Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE"}},"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE"}}]}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{}}}}},"STAGE DEPENDENCIES":{"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-0":{"DEPENDENT STAGES":"Stage-1"}}} diff --git a/ql/src/test/results/clientpositive/pointlookup.q.out b/ql/src/test/results/clientpositive/pointlookup.q.out index 7e19be4..560cdd2 100644 --- a/ql/src/test/results/clientpositive/pointlookup.q.out +++ b/ql/src/test/results/clientpositive/pointlookup.q.out @@ -48,7 +48,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -114,7 +114,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -180,7 +180,7 @@ STAGE PLANS: Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/pointlookup2.q.out b/ql/src/test/results/clientpositive/pointlookup2.q.out index 55edd90..85d6c13 100644 --- a/ql/src/test/results/clientpositive/pointlookup2.q.out +++ b/ql/src/test/results/clientpositive/pointlookup2.q.out @@ -169,13 +169,13 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + key expressions: key (type: int), value (type: string), ds (type: string) sort order: +++ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE - tag: -1 + tag: 0 auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -277,7 +277,7 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -290,7 +290,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2 + columns key,value,ds columns.types int:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true diff --git a/ql/src/test/results/clientpositive/pointlookup3.q.out b/ql/src/test/results/clientpositive/pointlookup3.q.out index 4cfb97e..16f453b 100644 --- a/ql/src/test/results/clientpositive/pointlookup3.q.out +++ b/ql/src/test/results/clientpositive/pointlookup3.q.out @@ -129,13 +129,13 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds1, ds2 Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) + key expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) sort order: ++++ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE - tag: -1 + tag: 0 auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -239,7 +239,7 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds1, ds2 Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -252,7 +252,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2,_col3 + columns key,value,ds1,ds2 columns.types int:string:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -367,14 +367,14 @@ STAGE PLANS: predicate: (key = 1) (type: boolean) Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), ds1 (type: string) - outputColumnNames: _col1, _col2 + expressions: ds1 (type: string), value (type: string) + outputColumnNames: ds1, value Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: 1 (type: int), _col1 (type: string), _col2 (type: string), '2001-04-08' (type: string) + key expressions: 1 (type: int), value (type: string), ds1 (type: string), '2001-04-08' (type: string) sort order: ++++ Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE - tag: -1 + tag: 0 auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -431,7 +431,7 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: 1 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), '2001-04-08' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds1, ds2 Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -444,7 +444,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2,_col3 + columns key,value,ds1,ds2 columns.types int:string:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true diff --git a/ql/src/test/results/clientpositive/ppd1.q.out b/ql/src/test/results/clientpositive/ppd1.q.out index 0497400..967b608 100644 --- a/ql/src/test/results/clientpositive/ppd1.q.out +++ b/ql/src/test/results/clientpositive/ppd1.q.out @@ -20,15 +20,22 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: (key > '2') (type: boolean) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -447,7 +454,7 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/ppd2.q.out b/ql/src/test/results/clientpositive/ppd2.q.out index d583b17..3bec2c8 100644 --- a/ql/src/test/results/clientpositive/ppd2.q.out +++ b/ql/src/test/results/clientpositive/ppd2.q.out @@ -64,12 +64,16 @@ STAGE PLANS: Filter Operator predicate: (_col1 > 1) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -300,14 +304,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: srcpart + alias: sub:srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (CASE WHEN (((value like 'aaa%') or (value like 'vvv%'))) THEN (1) ELSE (0) END > 0) (type: boolean) Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(key) (type: int) - outputColumnNames: _col0 + outputColumnNames: user_id Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -370,12 +374,16 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -468,12 +476,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -492,13 +504,17 @@ STAGE PLANS: Filter Operator predicate: (_col1 > 1) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/ppd_clusterby.q.out b/ql/src/test/results/clientpositive/ppd_clusterby.q.out index b21835f..9827d42 100644 --- a/ql/src/test/results/clientpositive/ppd_clusterby.q.out +++ b/ql/src/test/results/clientpositive/ppd_clusterby.q.out @@ -103,12 +103,16 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -252,12 +256,16 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce diff --git a/ql/src/test/results/clientpositive/ppd_constant_where.q.out b/ql/src/test/results/clientpositive/ppd_constant_where.q.out index c038ba3..d851432 100644 --- a/ql/src/test/results/clientpositive/ppd_constant_where.q.out +++ b/ql/src/test/results/clientpositive/ppd_constant_where.q.out @@ -32,15 +32,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/ppd_gby.q.out b/ql/src/test/results/clientpositive/ppd_gby.q.out index 87cb907..f06a862 100644 --- a/ql/src/test/results/clientpositive/ppd_gby.q.out +++ b/ql/src/test/results/clientpositive/ppd_gby.q.out @@ -19,51 +19,51 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((value > 'val_10') and (value > 'val_200')) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col1 > 'val_200') (type: boolean) - Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE + predicate: ((value > 'val_200') and (value > 'val_10')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE + expressions: value (type: string), key (type: string) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col1 > 30) or (_col0 < 'val_400')) (type: boolean) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + predicate: (($f1 > 30) or ($f0 < 'val_400')) (type: boolean) + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + expressions: $f0 (type: string) + outputColumnNames: c1 + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -239,18 +239,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((value > 'val_10') and (value > 'val_200')) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE @@ -265,14 +265,14 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col1 > 30) or (_col0 < 'val_400')) (type: boolean) + predicate: (($f1 > 30) or ($f0 < 'val_400')) (type: boolean) Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: $f0 (type: string) + outputColumnNames: c1 Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/ppd_gby2.q.out b/ql/src/test/results/clientpositive/ppd_gby2.q.out index bc00149..ef89359 100644 --- a/ql/src/test/results/clientpositive/ppd_gby2.q.out +++ b/ql/src/test/results/clientpositive/ppd_gby2.q.out @@ -22,54 +22,54 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((value > 'val_10') and (value > 'val_200')) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col1 > 'val_200') (type: boolean) - Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE + predicate: ((value > 'val_200') and (value > 'val_10')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE + expressions: value (type: string), key (type: string) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col1 > 30) or (_col0 < 'val_400')) (type: boolean) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + predicate: (($f1 > 30) or ($f0 < 'val_400')) (type: boolean) + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + expressions: $f1 (type: bigint), $f0 (type: string) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: bigint) + aggregations: max($f1) + keys: $f0 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -85,22 +85,22 @@ STAGE PLANS: key expressions: _col0 (type: bigint) sort order: + Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) keys: KEY._col0 (type: bigint) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col0 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + expressions: $f1 (type: string), $f0 (type: bigint) + outputColumnNames: _o__c0, c2 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -157,18 +157,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((value > 'val_10') and (value > 'val_200')) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE @@ -183,18 +183,18 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col1 > 30) or (_col0 < 'val_400')) (type: boolean) + predicate: (($f1 > 30) or ($f0 < 'val_400')) (type: boolean) Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint), _col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: $f1 (type: bigint), $f0 (type: string) + outputColumnNames: $f0, $f1 Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: bigint) + aggregations: max($f1) + keys: $f0 (type: bigint) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 18 Data size: 190 Basic stats: COMPLETE Column stats: NONE @@ -220,11 +220,11 @@ STAGE PLANS: aggregations: max(VALUE._col0) keys: KEY._col0 (type: bigint) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col0 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: $f1 (type: string), $f0 (type: bigint) + outputColumnNames: _o__c0, c2 Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/ppd_gby_join.q.out b/ql/src/test/results/clientpositive/ppd_gby_join.q.out index e3f71e7..ce9415f 100644 --- a/ql/src/test/results/clientpositive/ppd_gby_join.q.out +++ b/ql/src/test/results/clientpositive/ppd_gby_join.q.out @@ -32,85 +32,73 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((((key > '1') and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key < '400')) and (key > '2')) and (key <> '4')) and key is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE + predicate: ((((((key > '1') and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key < '400')) and (key > '2')) and (key <> '4')) (type: boolean) + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col0 > '20') and ((_col1 < 'val_50') or (_col0 > '2')) and (_col0 < '400')) (type: boolean) + predicate: (((((((key > '1') and (key > '20')) and (key < '400')) and (key > '2')) and (key <> '4')) and ((value < 'val_50') or (key > '2'))) and key is not null) (type: boolean) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 > '2') and (_col0 <> '4')) (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src + alias: src2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((key > '2') and (key <> '4')) and (key > '1')) and (key > '20')) and (key < '400')) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: (((((key > '2') and (key <> '4')) and (key > '1')) and (key > '20')) and (key < '400')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 <> '4') (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 > '1') and (_col0 > '20') and (_col0 < '400')) (type: boolean) + predicate: ((((((key > '2') and (key <> '4')) and (key > '1')) and (key > '20')) and (key < '400')) and key is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, key0 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean) + Select Operator + expressions: key (type: string), key0 (type: string) + outputColumnNames: c1, key Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Filter Operator + predicate: ((key > '50') or (c1 < '50')) (type: boolean) Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: c1 (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -127,15 +115,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -324,57 +316,57 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((((key > '1') and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key < '400')) and (key > '2')) and (key <> '4')) and key is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE + predicate: ((((((key > '1') and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key < '400')) and (key > '2')) and (key <> '4')) (type: boolean) + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src + alias: src2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((key > '2') and (key <> '4')) and (key > '1')) and (key > '20')) and (key < '400')) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: (((((key > '2') and (key <> '4')) and (key > '1')) and (key > '20')) and (key < '400')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, key0 + Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean) - Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + predicate: ((key0 > '50') or (key < '50')) (type: boolean) + Statistics: Num rows: 4 Data size: 46 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 4 Data size: 46 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 46 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -390,22 +382,26 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 46 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 2 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 2 Data size: 23 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 23 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/ppd_join.q.out b/ql/src/test/results/clientpositive/ppd_join.q.out index 58c4e43..432f392 100644 --- a/ql/src/test/results/clientpositive/ppd_join.q.out +++ b/ql/src/test/results/clientpositive/ppd_join.q.out @@ -29,81 +29,69 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((((key > '1') and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key < '400')) and (key > '2')) and (key <> '4')) and key is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE + predicate: ((((((key > '1') and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key < '400')) and (key > '2')) and (key <> '4')) (type: boolean) + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col0 > '20') and ((_col1 < 'val_50') or (_col0 > '2')) and (_col0 < '400')) (type: boolean) + predicate: (((((((key > '1') and (key > '20')) and (key < '400')) and (key > '2')) and (key <> '4')) and ((value < 'val_50') or (key > '2'))) and key is not null) (type: boolean) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 > '2') and (_col0 <> '4')) (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src + alias: src2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((key > '2') and (key <> '4')) and (key > '1')) and (key > '20')) and (key < '400')) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: (((((key > '2') and (key <> '4')) and (key > '1')) and (key > '20')) and (key < '400')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 <> '4') (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 > '1') and (_col0 > '20') and (_col0 < '400')) (type: boolean) + predicate: ((((((key > '2') and (key <> '4')) and (key > '1')) and (key > '20')) and (key < '400')) and key is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, key0, value0 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean) + Select Operator + expressions: key (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: c1, key, value Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 + Filter Operator + predicate: ((key > '50') or (c1 < '50')) (type: boolean) Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: c1 (type: string), value (type: string) + outputColumnNames: c1, c4 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -576,55 +564,55 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((((key > '1') and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key < '400')) and (key > '2')) and (key <> '4')) and key is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE + predicate: ((((((key > '1') and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key < '400')) and (key > '2')) and (key <> '4')) (type: boolean) + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src + alias: src2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((key > '2') and (key <> '4')) and (key > '1')) and (key > '20')) and (key < '400')) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: (((((key > '2') and (key <> '4')) and (key > '1')) and (key > '20')) and (key < '400')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, key0, value0 + Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean) - Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + predicate: ((key0 > '50') or (key < '50')) (type: boolean) + Statistics: Num rows: 4 Data size: 46 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value0 (type: string) + outputColumnNames: c1, c4 + Statistics: Num rows: 4 Data size: 46 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 46 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_join2.q.out b/ql/src/test/results/clientpositive/ppd_join2.q.out index e99839e..8cffe0d 100644 --- a/ql/src/test/results/clientpositive/ppd_join2.q.out +++ b/ql/src/test/results/clientpositive/ppd_join2.q.out @@ -36,128 +36,102 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((((key <> '302') and (key <> '311')) and ((value <> 'val_50') or (key > '1'))) and (key < '400')) and (key <> '305')) and (key <> '14')) and key is not null) and value is not null) (type: boolean) - Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE + predicate: ((((((((key <> '302') and key is not null) and value is not null) and (key < '400')) and (key <> '311')) and ((value <> 'val_50') or (key > '1'))) and (key <> '305')) and (key <> '14')) (type: boolean) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col0 <> '311') and ((_col1 <> 'val_50') or (_col0 > '1')) and (_col0 < '400')) (type: boolean) - Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 <> '305') and (_col0 <> '14')) (type: boolean) - Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 7 Data size: 74 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 7 Data size: 74 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + predicate: ((((((((key <> '302') and (key < '400')) and (key <> '311')) and (key <> '305')) and (key <> '14')) and ((value <> 'val_50') or (key > '1'))) and value is not null) and key is not null) (type: boolean) + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) TableScan - alias: src + alias: src2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((key <> '305') and (key <> '14')) and (key <> '302')) and (key <> '311')) and (key < '400')) and key is not null) (type: boolean) + predicate: ((((((key <> '305') and key is not null) and (key <> '14')) and (key <> '302')) and (key < '400')) and (key <> '311')) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 <> '14') (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 <> '302') and (_col0 <> '311') and (_col0 < '400')) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + predicate: ((((((key <> '305') and (key <> '14')) and (key <> '302')) and (key < '400')) and (key <> '311')) and key is not null) (type: boolean) + Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col2 <> '10') or (_col0 <> '10')) (type: boolean) + predicate: ((key0 <> '10') or (key <> '10')) (type: boolean) Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col1 is not null (type: boolean) - Statistics: Num rows: 8 Data size: 86 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: src + alias: src3:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key <> '306') and (sqrt(key) <> 13.0)) and value is not null) (type: boolean) + predicate: (((key <> '306') and value is not null) and (sqrt(key) <> 13.0)) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (sqrt(_col0) <> 13.0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + predicate: (((sqrt(key) <> 13.0) and value is not null) and (key <> '306')) (type: boolean) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 8 Data size: 86 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col3 (type: string) + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: string), value0 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col1, _col4 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key0, value00 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1 + expressions: key0 (type: string), value00 (type: string) + outputColumnNames: c1, c4 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1751,97 +1725,93 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((((key <> '302') and (key <> '311')) and ((value <> 'val_50') or (key > '1'))) and (key < '400')) and (key <> '305')) and (key <> '14')) and key is not null) and value is not null) (type: boolean) - Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE + predicate: ((((((((key <> '302') and key is not null) and value is not null) and (key < '400')) and (key <> '311')) and ((value <> 'val_50') or (key > '1'))) and (key <> '305')) and (key <> '14')) (type: boolean) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) TableScan - alias: src + alias: src2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((key <> '305') and (key <> '14')) and (key <> '302')) and (key <> '311')) and (key < '400')) and key is not null) (type: boolean) + predicate: ((((((key <> '305') and key is not null) and (key <> '14')) and (key <> '302')) and (key < '400')) and (key <> '311')) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col2 <> '10') or (_col0 <> '10')) (type: boolean) + predicate: ((key0 <> '10') or (key <> '10')) (type: boolean) Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: src + alias: src3:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key <> '306') and (sqrt(key) <> 13.0)) and value is not null) (type: boolean) + predicate: (((key <> '306') and value is not null) and (sqrt(key) <> 13.0)) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: value (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: value (type: string) Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col3 (type: string) + value expressions: key (type: string), value0 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col1, _col4 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key0, value00 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1 + expressions: key0 (type: string), value00 (type: string) + outputColumnNames: c1, c4 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/ppd_join3.q.out b/ql/src/test/results/clientpositive/ppd_join3.q.out index f2b0b60..ff6b991 100644 --- a/ql/src/test/results/clientpositive/ppd_join3.q.out +++ b/ql/src/test/results/clientpositive/ppd_join3.q.out @@ -27,146 +27,118 @@ ON src1.c1 = src3.c5 WHERE src1.c1 > '0' and (src1.c2 <> 'val_500' or src1.c1 > '1') and (src2.c3 > '10' or src1.c1 <> '10') and (src2.c3 <> '4') and (src3.c5 <> '1') POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-1 + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((((((key <> '11') and (key > '0')) and ((value <> 'val_500') or (key > '1'))) and (key < '400')) and (key <> '12')) and (key <> '4')) and key is not null) and (key <> '13')) and (key <> '1')) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: (((((((key <> '11') and key is not null) and (key < '400')) and (key > '0')) and ((value <> 'val_500') or (key > '1'))) and (key <> '12')) and (key <> '4')) (type: boolean) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col0 > '0') and ((_col1 <> 'val_500') or (_col0 > '1')) and (_col0 < '400')) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 <> '12') and (_col0 <> '4')) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + predicate: (((((((key <> '11') and (key < '400')) and (key > '0')) and (key <> '12')) and (key <> '4')) and ((value <> 'val_500') or (key > '1'))) and key is not null) (type: boolean) + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src + alias: src2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((((key <> '12') and (key <> '4')) and (key <> '11')) and (key > '0')) and (key < '400')) and key is not null) and (key <> '13')) and (key <> '1')) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((((((key <> '12') and key is not null) and (key <> '4')) and (key <> '11')) and (key < '400')) and (key > '0')) (type: boolean) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 <> '4') (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 <> '11') and (_col0 > '0') and (_col0 < '400')) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + predicate: ((((((key <> '12') and (key <> '4')) and (key <> '11')) and (key < '400')) and (key > '0')) and key is not null) (type: boolean) + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col1 > '10') or (_col0 <> '10')) (type: boolean) - Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 <> '13') and (_col0 <> '1')) (type: boolean) - Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, key0, value0 + Statistics: Num rows: 2 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: c1, key, value + Statistics: Num rows: 2 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((((((((c1 <> '11') and (c1 < '400')) and (c1 > '0')) and (c1 <> '12')) and (c1 <> '4')) and (c1 <> '13')) and (c1 <> '1')) and ((key > '10') or (c1 <> '10'))) (type: boolean) + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-1 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: src + Reduce Output Operator + key expressions: c1 (type: string) + sort order: + + Map-reduce partition columns: c1 (type: string) + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + TableScan + alias: src3:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((((key <> '13') and (key <> '1')) and (key <> '11')) and (key > '0')) and (key < '400')) and (key <> '12')) and (key <> '4')) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((((((((key <> '13') and key is not null) and (key <> '1')) and (key <> '11')) and (key < '400')) and (key > '0')) and (key <> '12')) and (key <> '4')) (type: boolean) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 <> '1') (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 <> '11') and (_col0 > '0') and (_col0 < '400') and (_col0 <> '12') and (_col0 <> '4')) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: string) + predicate: ((((((((key <> '13') and (key <> '1')) and (key <> '11')) and (key < '400')) and (key > '0')) and (key <> '12')) and (key <> '4')) and key is not null) (type: boolean) + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col3 - Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + 0 c1 (type: string) + 1 key (type: string) + outputColumnNames: c1, value + Statistics: Num rows: 2 Data size: 23 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + expressions: c1 (type: string), value (type: string) + outputColumnNames: c1, c4 + Statistics: Num rows: 2 Data size: 23 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 23 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1804,61 +1776,61 @@ ON src1.c1 = src3.c5 WHERE src1.c1 > '0' and (src1.c2 <> 'val_500' or src1.c1 > '1') and (src2.c3 > '10' or src1.c1 <> '10') and (src2.c3 <> '4') and (src3.c5 <> '1') POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-1 + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((((((key <> '11') and (key > '0')) and ((value <> 'val_500') or (key > '1'))) and (key < '400')) and (key <> '12')) and (key <> '4')) and key is not null) and (key <> '13')) and (key <> '1')) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: (((((((key <> '11') and key is not null) and (key < '400')) and (key > '0')) and ((value <> 'val_500') or (key > '1'))) and (key <> '12')) and (key <> '4')) (type: boolean) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src + alias: src2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((((key <> '12') and (key <> '4')) and (key <> '11')) and (key > '0')) and (key < '400')) and key is not null) and (key <> '13')) and (key <> '1')) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((((((key <> '12') and key is not null) and (key <> '4')) and (key <> '11')) and (key < '400')) and (key > '0')) (type: boolean) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, key0, value0 + Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col1 > '10') or (_col0 <> '10')) (type: boolean) - Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE + predicate: (((((((((key0 > '10') or (key <> '10')) and (key <> '11')) and (key < '400')) and (key > '0')) and (key <> '12')) and (key <> '4')) and (key <> '13')) and (key <> '1')) (type: boolean) + Statistics: Num rows: 4 Data size: 43 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value0 (type: string) + outputColumnNames: c1, value + Statistics: Num rows: 4 Data size: 43 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1866,47 +1838,47 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-1 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: src + Reduce Output Operator + key expressions: c1 (type: string) + sort order: + + Map-reduce partition columns: c1 (type: string) + Statistics: Num rows: 4 Data size: 43 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + TableScan + alias: src3:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((((key <> '13') and (key <> '1')) and (key <> '11')) and (key > '0')) and (key < '400')) and (key <> '12')) and (key <> '4')) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((((((((key <> '13') and key is not null) and (key <> '1')) and (key <> '11')) and (key < '400')) and (key > '0')) and (key <> '12')) and (key <> '4')) (type: boolean) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col3 - Statistics: Num rows: 33 Data size: 358 Basic stats: COMPLETE Column stats: NONE + 0 c1 (type: string) + 1 key (type: string) + outputColumnNames: c1, value + Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 33 Data size: 358 Basic stats: COMPLETE Column stats: NONE + expressions: c1 (type: string), value (type: string) + outputColumnNames: c1, c4 + Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 33 Data size: 358 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_join_filter.q.out b/ql/src/test/results/clientpositive/ppd_join_filter.q.out index e99986f..dbc562b 100644 --- a/ql/src/test/results/clientpositive/ppd_join_filter.q.out +++ b/ql/src/test/results/clientpositive/ppd_join_filter.q.out @@ -129,7 +129,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: b:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator @@ -138,22 +138,26 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col0) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: min(key) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -202,44 +206,36 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_1:$hdt$_1:a] + /src [b:src] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, $f1 + Statistics: Num rows: 62 Data size: 658 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((UDFToDouble(_col1) + 1.0) < 5.0) (type: boolean) - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0) (type: double), (UDFToDouble(_col1) + 3.0) (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE - Filter Operator - isSamplingPred: false - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 21 Data size: 222 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types string,double,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + predicate: (key is not null and ((UDFToDouble($f1) + 1.0) < 5.0)) (type: boolean) + Statistics: Num rows: 10 Data size: 106 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns key,$f1 + columns.types string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Map Reduce @@ -254,40 +250,40 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: _col0 is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE tag: 0 auto parallelism: false TableScan GatherStats: false Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 21 Data size: 222 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 10 Data size: 106 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: double), _col2 (type: double) + value expressions: $f1 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10003 + base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2 - columns.types string,double,double + columns key,$f1 + columns.types string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -295,8 +291,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2 - columns.types string,double,double + columns key,$f1 + columns.types string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -345,7 +341,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_0:a] + /src [a] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: @@ -353,13 +349,13 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), (UDFToDouble($f1) + 2.0) (type: double), (UDFToDouble($f1) + 3.0) (type: double) + outputColumnNames: key, k2, k3 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -372,7 +368,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2 + columns key,k2,k3 columns.types string:double:double escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -554,7 +550,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: b:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator @@ -563,11 +559,11 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) - keys: _col0 (type: string) + aggregations: min(key) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -627,40 +623,36 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_1:$hdt$_1:a] + /src [b:src] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((UDFToDouble(_col1) + 1.0) < 5.0) (type: boolean) + predicate: ((UDFToDouble($f1) + 1.0) < 5.0) (type: boolean) Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0) (type: double), (UDFToDouble(_col1) + 3.0) (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types string,double,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns key,$f1 + columns.types string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Map Reduce @@ -675,36 +667,36 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE tag: 0 auto parallelism: false TableScan GatherStats: false Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: double), _col2 (type: double) + value expressions: $f1 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10003 + base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2 - columns.types string,double,double + columns key,$f1 + columns.types string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -712,8 +704,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2 - columns.types string,double,double + columns key,$f1 + columns.types string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -762,7 +754,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_0:a] + /src [a] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: @@ -770,13 +762,13 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), (UDFToDouble($f1) + 2.0) (type: double), (UDFToDouble($f1) + 3.0) (type: double) + outputColumnNames: key, k2, k3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -789,7 +781,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2 + columns key,k2,k3 columns.types string:double:double escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -971,27 +963,31 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: b:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col0) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: min(key) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1040,44 +1036,36 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_1:$hdt$_1:a] + /src [b:src] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, $f1 + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((UDFToDouble(_col1) + 1.0) < 5.0) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0) (type: double), (UDFToDouble(_col1) + 3.0) (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Filter Operator - isSamplingPred: false - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 42 Data size: 445 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types string,double,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + predicate: ((UDFToDouble($f1) + 1.0) < 5.0) (type: boolean) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns key,$f1 + columns.types string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Map Reduce @@ -1088,40 +1076,40 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: _col0 is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE tag: 0 auto parallelism: false TableScan GatherStats: false Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 42 Data size: 445 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: double), _col2 (type: double) + value expressions: $f1 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10003 + base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2 - columns.types string,double,double + columns key,$f1 + columns.types string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -1129,8 +1117,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2 - columns.types string,double,double + columns key,$f1 + columns.types string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -1179,7 +1167,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_0:a] + /src [a] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: @@ -1187,13 +1175,13 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), (UDFToDouble($f1) + 2.0) (type: double), (UDFToDouble($f1) + 3.0) (type: double) + outputColumnNames: key, k2, k3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1206,7 +1194,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2 + columns key,k2,k3 columns.types string:double:double escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -1388,7 +1376,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: b:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator @@ -1397,11 +1385,11 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) - keys: _col0 (type: string) + aggregations: min(key) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -1461,40 +1449,36 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_1:$hdt$_1:a] + /src [b:src] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((UDFToDouble(_col1) + 1.0) < 5.0) (type: boolean) + predicate: ((UDFToDouble($f1) + 1.0) < 5.0) (type: boolean) Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0) (type: double), (UDFToDouble(_col1) + 3.0) (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types string,double,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns key,$f1 + columns.types string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Map Reduce @@ -1509,36 +1493,36 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE tag: 0 auto parallelism: false TableScan GatherStats: false Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: double), _col2 (type: double) + value expressions: $f1 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10003 + base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2 - columns.types string,double,double + columns key,$f1 + columns.types string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -1546,8 +1530,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2 - columns.types string,double,double + columns key,$f1 + columns.types string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -1596,7 +1580,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_0:a] + /src [a] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: @@ -1604,13 +1588,13 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), (UDFToDouble($f1) + 2.0) (type: double), (UDFToDouble($f1) + 3.0) (type: double) + outputColumnNames: key, k2, k3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1623,7 +1607,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2 + columns key,k2,k3 columns.types string:double:double escape.delim \ hive.serialization.extend.additional.nesting.levels true diff --git a/ql/src/test/results/clientpositive/ppd_outer_join1.q.out b/ql/src/test/results/clientpositive/ppd_outer_join1.q.out index d021d5d..cca2460 100644 --- a/ql/src/test/results/clientpositive/ppd_outer_join1.q.out +++ b/ql/src/test/results/clientpositive/ppd_outer_join1.q.out @@ -36,49 +36,59 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Filter Operator + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Filter Operator + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean) - Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + predicate: ((UDFToDouble(key0) > 15.0) and (UDFToDouble(key0) < 25.0)) (type: boolean) + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -146,49 +156,53 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean) + predicate: ((UDFToDouble(key0) > 15.0) and (UDFToDouble(key0) < 25.0)) (type: boolean) Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/ppd_outer_join2.q.out b/ql/src/test/results/clientpositive/ppd_outer_join2.q.out index d965d5b..1c5ce23 100644 --- a/ql/src/test/results/clientpositive/ppd_outer_join2.q.out +++ b/ql/src/test/results/clientpositive/ppd_outer_join2.q.out @@ -32,62 +32,60 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col0 > '15') and (_col0 < '25')) (type: boolean) + predicate: ((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) (type: boolean) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col0 > '10') and (_col0 < '20')) (type: boolean) + predicate: ((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) (type: boolean) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -271,50 +269,54 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/ppd_outer_join3.q.out b/ql/src/test/results/clientpositive/ppd_outer_join3.q.out index f1fbbd6..9cf6411 100644 --- a/ql/src/test/results/clientpositive/ppd_outer_join3.q.out +++ b/ql/src/test/results/clientpositive/ppd_outer_join3.q.out @@ -32,62 +32,60 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col0 > '15') and (_col0 < '25')) (type: boolean) + predicate: ((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) (type: boolean) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col0 > '10') and (_col0 < '20')) (type: boolean) + predicate: ((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) (type: boolean) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -271,50 +269,54 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/ppd_outer_join4.q.out b/ql/src/test/results/clientpositive/ppd_outer_join4.q.out index 9997166..d997dd7 100644 --- a/ql/src/test/results/clientpositive/ppd_outer_join4.q.out +++ b/ql/src/test/results/clientpositive/ppd_outer_join4.q.out @@ -39,115 +39,107 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) and key is not null) and (sqrt(key) <> 13.0)) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col0 > '15') and (_col0 < '25')) (type: boolean) + predicate: ((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) (type: boolean) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) and key is not null) and (sqrt(key) <> 13.0)) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col0 > '10') and (_col0 < '20')) (type: boolean) + predicate: ((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) (type: boolean) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (sqrt(_col0) <> 13.0) (type: boolean) + predicate: (((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) and (sqrt(key) <> 13.0)) (type: boolean) Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) + value expressions: value (type: string), key0 (type: string), value0 (type: string) TableScan - alias: a + alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((sqrt(key) <> 13.0) and (key > '10')) and (key < '20')) and (key > '15')) and (key < '25')) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: (((((sqrt(key) <> 13.0) and (key > '10')) and (key < '20')) and (key > '15')) and (key < '25')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col0 > '10') and (_col0 < '20') and (_col0 > '15') and (_col0 < '25')) (type: boolean) + predicate: (((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) and (sqrt(key) <> 13.0)) (type: boolean) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0, key1 Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string), key1 (type: string) + outputColumnNames: key, value, key0, value0, key1 Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -448,91 +440,98 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) and key is not null) and (sqrt(key) <> 13.0)) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) and key is not null) and (sqrt(key) <> 13.0)) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) and (sqrt(key) <> 13.0)) (type: boolean) + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string), key0 (type: string), value0 (type: string) TableScan - alias: a + alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((sqrt(key) <> 13.0) and (key > '10')) and (key < '20')) and (key > '15')) and (key < '25')) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: (((((sqrt(key) <> 13.0) and (key > '10')) and (key < '20')) and (key > '15')) and (key < '25')) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 3 Data size: 37 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 3 Data size: 37 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0, key1 + Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string), key1 (type: string) + outputColumnNames: key, value, key0, value0, key1 + Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/ppd_random.q.out b/ql/src/test/results/clientpositive/ppd_random.q.out index ff9a812..a878700 100644 --- a/ql/src/test/results/clientpositive/ppd_random.q.out +++ b/ql/src/test/results/clientpositive/ppd_random.q.out @@ -25,65 +25,69 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > '2') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: ((key > '2') and key is not null) (type: boolean) + Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src + alias: src2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > '2') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: (key is not null and (key > '2')) (type: boolean) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (rand() > 0.5) (type: boolean) - Statistics: Num rows: 30 Data size: 319 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 30 Data size: 319 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 30 Data size: 319 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value + Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (rand() > 0.5) (type: boolean) + Statistics: Num rows: 10 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 10 Data size: 108 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 108 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -118,59 +122,63 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > '2') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src + alias: src2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > '2') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (rand() > 0.5) (type: boolean) - Statistics: Num rows: 60 Data size: 639 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (rand() > 0.5) (type: boolean) Statistics: Num rows: 60 Data size: 639 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 60 Data size: 639 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 60 Data size: 639 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/ppd_transform.q.out b/ql/src/test/results/clientpositive/ppd_transform.q.out index 17248e4..1ffc641 100644 --- a/ql/src/test/results/clientpositive/ppd_transform.q.out +++ b/ql/src/test/results/clientpositive/ppd_transform.q.out @@ -56,13 +56,17 @@ STAGE PLANS: Filter Operator predicate: (_col0 < 100) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -392,23 +396,31 @@ STAGE PLANS: Filter Operator predicate: ((_col0 = 'a') or (_col0 = 'b')) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((_col0 = 'c') or (_col0 = 'd')) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Move Operator diff --git a/ql/src/test/results/clientpositive/ppd_udf_case.q.out b/ql/src/test/results/clientpositive/ppd_udf_case.q.out index ddf1abd..1fdfc265 100644 --- a/ql/src/test/results/clientpositive/ppd_udf_case.q.out +++ b/ql/src/test/results/clientpositive/ppd_udf_case.q.out @@ -37,75 +37,76 @@ STAGE PLANS: alias: a Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (CASE (key) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END and key is not null) (type: boolean) + predicate: (key is not null and CASE (key) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col3 + expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) + outputColumnNames: key, value, ds, hr Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + predicate: (((ds = '2008-04-08') and CASE (key) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END) and key is not null) (type: boolean) + Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col3 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string), '2008-04-08' (type: string), hr (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (CASE (key) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END and key is not null) (type: boolean) + predicate: (key is not null and CASE (key) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col3 + expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) + outputColumnNames: key, value, ds, hr Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: CASE (_col0) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 63 Data size: 669 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 63 Data size: 669 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col3 (type: string) + predicate: ((CASE (key) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END and (ds = '2008-04-08')) and key is not null) (type: boolean) + Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string), ds (type: string), hr (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col7 - Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, ds, hr, key0, value0, ds0, hr0 + Statistics: Num rows: 34 Data size: 361 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string), key0 (type: string), value0 (type: string), ds0 (type: string), hr0 (type: string) + outputColumnNames: key, value, ds, hr, key0, value0, ds0, hr0 + Statistics: Num rows: 34 Data size: 361 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), '2008-04-08' (type: string), _col7 (type: string) + key expressions: key (type: string), value (type: string), ds (type: string), hr (type: string), key0 (type: string), value0 (type: string), ds0 (type: string), hr0 (type: string) sort order: ++++++++ - Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 361 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey7 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: string), KEY.reducesinkkey7 (type: string) + outputColumnNames: key, value, ds, hr, key0, value0, ds0, hr0 + Statistics: Num rows: 34 Data size: 361 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 361 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -192,62 +193,66 @@ STAGE PLANS: alias: a Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (CASE (key) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END and key is not null) (type: boolean) + predicate: (key is not null and CASE (key) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col3 + expressions: hr (type: string), key (type: string), value (type: string) + outputColumnNames: hr, key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col3 (type: string) + value expressions: value (type: string), '2008-04-08' (type: string), hr (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (CASE (key) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END and key is not null) (type: boolean) + predicate: (key is not null and CASE (key) WHEN ('27') THEN (true) WHEN ('38') THEN (false) ELSE (null) END) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col3 + expressions: hr (type: string), key (type: string), value (type: string) + outputColumnNames: hr, key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col3 (type: string) + value expressions: value (type: string), '2008-04-08' (type: string), hr (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col7 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, ds, hr, key0, value0, ds0, hr0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string), key0 (type: string), value0 (type: string), ds0 (type: string), hr0 (type: string) + outputColumnNames: key, value, ds, hr, key0, value0, ds0, hr0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), '2008-04-08' (type: string), _col7 (type: string) + key expressions: key (type: string), value (type: string), ds (type: string), hr (type: string), key0 (type: string), value0 (type: string), ds0 (type: string), hr0 (type: string) sort order: ++++++++ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey7 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: string), KEY.reducesinkkey7 (type: string) + outputColumnNames: key, value, ds, hr, key0, value0, ds0, hr0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/ppd_udf_col.q.out b/ql/src/test/results/clientpositive/ppd_udf_col.q.out index 7c963fb..8bb091e 100644 --- a/ql/src/test/results/clientpositive/ppd_udf_col.q.out +++ b/ql/src/test/results/clientpositive/ppd_udf_col.q.out @@ -17,19 +17,21 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 100.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: '100.0' (type: string) + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (rand() <= 0.1) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '100' (type: string), rand() (type: double) - outputColumnNames: _col0, _col1 + expressions: key (type: string), rand() (type: double) + outputColumnNames: key, randum123 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -68,33 +70,32 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: s:a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 100.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: '100.0' (type: string) + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (rand() <= 0.1) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (rand() > 0.1) (type: boolean) + predicate: ((rand() > 0.1) and (rand() <= 0.1)) (type: boolean) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), rand() (type: double) + outputColumnNames: key, randum123 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '100' (type: string), rand() (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 20 + Limit + Number of rows: 20 + Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -121,25 +122,29 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Filter Operator - predicate: false (type: boolean) + Select Operator + expressions: '100.0' (type: string) + outputColumnNames: key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator - expressions: '100' (type: string), rand() (type: double), '4' (type: string) - outputColumnNames: _col0, _col1, _col2 + Filter Operator + predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), rand() (type: double), '4' (type: string) + outputColumnNames: key, randum123, h4 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -166,21 +171,21 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) = 100.0) and ((UDFToDouble(value) * 10.0) <= 200.0)) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col1 + expressions: '100.0' (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(_col1) * 10.0) <= 200.0) (type: boolean) + predicate: ((UDFToDouble(value) * 10.0) <= 200.0) (type: boolean) Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '100' (type: string), rand() (type: double), (UDFToDouble(_col1) * 10.0) (type: double) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), rand() (type: double), (UDFToDouble(value) * 10.0) (type: double) + outputColumnNames: key, randum123, v10 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -215,19 +220,21 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 100.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: '100.0' (type: string) + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (rand() <= 0.1) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '100' (type: string), rand() (type: double) - outputColumnNames: _col0, _col1 + expressions: key (type: string), rand() (type: double) + outputColumnNames: key, randum123 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -266,33 +273,32 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: s:a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 100.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: '100.0' (type: string) + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (rand() <= 0.1) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (rand() > 0.1) (type: boolean) + predicate: ((rand() > 0.1) and (rand() <= 0.1)) (type: boolean) + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), rand() (type: double) + outputColumnNames: key, randum123 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '100' (type: string), rand() (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 20 + Limit + Number of rows: 20 + Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -319,14 +325,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator - expressions: '100' (type: string), rand() (type: double), '4' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: '100.0' (type: string), rand() (type: double), '4' (type: string) + outputColumnNames: key, randum123, h4 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE File Output Operator compressed: false @@ -361,14 +367,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) = 100.0) and ((UDFToDouble(value) * 10.0) <= 200.0)) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '100' (type: string), rand() (type: double), (UDFToDouble(value) * 10.0) (type: double) - outputColumnNames: _col0, _col1, _col2 + expressions: '100.0' (type: string), rand() (type: double), (UDFToDouble(value) * 10.0) (type: double) + outputColumnNames: key, randum123, v10 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/ppd_union.q.out b/ql/src/test/results/clientpositive/ppd_union.q.out index 166eff1..5ebfda1 100644 --- a/ql/src/test/results/clientpositive/ppd_union.q.out +++ b/ql/src/test/results/clientpositive/ppd_union.q.out @@ -25,49 +25,61 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1:unioned_query-subquery1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key < '100') and (key > '4')) and (value > 'val_4')) (type: boolean) Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col0 > '4') and (_col1 > 'val_4')) (type: boolean) - Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE + predicate: (((key > '4') and (value > 'val_4')) and (key < '100')) (type: boolean) + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: src + alias: null-subquery2:unioned_query-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > '150') and (key > '4')) and (value > 'val_4')) (type: boolean) Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col0 > '4') and (_col1 > 'val_4')) (type: boolean) - Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + predicate: (((key > '4') and (value > 'val_4')) and (key > '150')) (type: boolean) + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -293,43 +305,51 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1:unioned_query-subquery1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key < '100') and (key > '4')) and (value > 'val_4')) (type: boolean) Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: src + alias: null-subquery2:unioned_query-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > '150') and (key > '4')) and (value > 'val_4')) (type: boolean) Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/ppd_union_view.q.out b/ql/src/test/results/clientpositive/ppd_union_view.q.out index 716d59f..fd7e426 100644 --- a/ql/src/test/results/clientpositive/ppd_union_view.q.out +++ b/ql/src/test/results/clientpositive/ppd_union_view.q.out @@ -511,52 +511,44 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: ((ds = '2011-10-15') and keymap is not null) (type: boolean) + predicate: (keymap is not null and (ds = '2011-10-15')) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: keymap (type: string), value (type: string) - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: keymap (type: string), '2011-10-15' (type: string) + sort order: ++ + Map-reduce partition columns: keymap (type: string), '2011-10-15' (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - tag: 0 - value expressions: _col1 (type: string) - auto parallelism: false + tag: 0 + value expressions: value (type: string) + auto parallelism: false TableScan alias: t1_mapping Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (('2011-10-15' = ds) and keymap is not null) (type: boolean) + predicate: (keymap is not null and (ds = '2011-10-15')) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: key (type: string), keymap (type: string) - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: keymap (type: string), '2011-10-15' (type: string) + sort order: ++ + Map-reduce partition columns: keymap (type: string), '2011-10-15' (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - tag: 1 - value expressions: _col0 (type: string) - auto parallelism: false + tag: 1 + value expressions: key (type: string) + auto parallelism: false Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col1, _col3 + 0 keymap (type: string), ds (type: string) + 1 keymap (type: string), ds (type: string) + outputColumnNames: _col1, _col6 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col3 (type: string), _col1 (type: string) + expressions: _col6 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator @@ -713,7 +705,7 @@ STAGE PLANS: name: default.t1_new name: default.t1_new Truncated Path -> Alias: - /t1_new/ds=2011-10-15 [null-subquery1:$hdt$_0-subquery1:t1_new] + /t1_new/ds=2011-10-15 [t1-subquery1:subq-subquery1:t1_new] #### A masked pattern was here #### Stage: Stage-0 diff --git a/ql/src/test/results/clientpositive/ppd_vc.q.out b/ql/src/test/results/clientpositive/ppd_vc.q.out index a16058c..5a33b78 100644 --- a/ql/src/test/results/clientpositive/ppd_vc.q.out +++ b/ql/src/test/results/clientpositive/ppd_vc.q.out @@ -47,7 +47,7 @@ STAGE PLANS: Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -60,7 +60,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2,_col3 + columns key,value,ds,hr columns.types string:string:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -418,34 +418,34 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE tag: 0 auto parallelism: false TableScan - alias: srcpart + alias: b:srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (((BLOCK__OFFSET__INSIDE__FILE < 100) and (BLOCK__OFFSET__INSIDE__FILE < 50)) and key is not null) (type: boolean) + predicate: ((key is not null and (BLOCK__OFFSET__INSIDE__FILE < 100)) and (BLOCK__OFFSET__INSIDE__FILE < 50)) (type: boolean) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: key, value, ds, hr, BLOCK__OFFSET__INSIDE__FILE Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: bigint) + value expressions: value (type: string), ds (type: string), hr (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -679,24 +679,24 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:$hdt$_1:srcpart] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:$hdt$_1:srcpart] - /srcpart/ds=2008-04-09/hr=11 [$hdt$_1:$hdt$_1:srcpart] - /srcpart/ds=2008-04-09/hr=12 [$hdt$_1:$hdt$_1:srcpart] + /src [a] + /srcpart/ds=2008-04-08/hr=11 [b:srcpart] + /srcpart/ds=2008-04-08/hr=12 [b:srcpart] + /srcpart/ds=2008-04-09/hr=11 [b:srcpart] + /srcpart/ds=2008-04-09/hr=12 [b:srcpart] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3, _col4, _col5 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key0, value, ds, hr, BLOCK__OFFSET__INSIDE__FILE Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: key0 (type: string), value (type: string), ds (type: string), hr (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) + outputColumnNames: key, value, ds, hr, block__offset__inside__file Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -707,7 +707,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2,_col3,_col4 + columns key,value,ds,hr,block__offset__inside__file columns.types string,string,string,string,bigint escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -722,22 +722,22 @@ STAGE PLANS: TableScan GatherStats: false Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string), _col4 (type: bigint) + key expressions: ds (type: string), hr (type: string), block__offset__inside__file (type: bigint) sort order: +++ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: string), _col1 (type: string) + tag: 0 + value expressions: key (type: string), value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10003 + base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2,_col3,_col4 + columns key,value,ds,hr,block__offset__inside__file columns.types string,string,string,string,bigint escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -746,7 +746,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2,_col3,_col4 + columns key,value,ds,hr,block__offset__inside__file columns.types string,string,string,string,bigint escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -756,8 +756,8 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: VALUE.key (type: string), VALUE.value (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: bigint) + outputColumnNames: key, value, ds, hr, block__offset__inside__file Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -770,7 +770,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2,_col3,_col4 + columns key,value,ds,hr,block__offset__inside__file columns.types string:string:string:string:bigint escape.delim \ hive.serialization.extend.additional.nesting.levels true diff --git a/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out b/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out index 6fe7984..c846a95 100644 --- a/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out +++ b/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out @@ -78,7 +78,7 @@ STAGE PLANS: Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: user_id, value Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -91,7 +91,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1 + columns user_id,value columns.types int:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -304,35 +304,39 @@ STAGE PLANS: alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((ds = '2008-04-08') and (CASE WHEN (((value like 'aaa%') or (value like 'vvv%'))) THEN (1) ELSE (0) END > 0)) (type: boolean) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(key) (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1 - columns.types int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: key (type: string), value (type: string), ds (type: string) + outputColumnNames: key, value, ds + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Filter Operator + isSamplingPred: false + predicate: ((ds = '2008-04-08') and (CASE WHEN (((value like 'aaa%') or (value like 'vvv%'))) THEN (1) ELSE (0) END > 0)) (type: boolean) + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: UDFToInteger(key) (type: int), value (type: string) + outputColumnNames: user_id, value + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns user_id,value + columns.types int:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: diff --git a/ql/src/test/results/clientpositive/ppr_pushdown3.q.out b/ql/src/test/results/clientpositive/ppr_pushdown3.q.out index 0d2038b..7101af8 100644 --- a/ql/src/test/results/clientpositive/ppr_pushdown3.q.out +++ b/ql/src/test/results/clientpositive/ppr_pushdown3.q.out @@ -18,7 +18,7 @@ STAGE PLANS: Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE ListSink @@ -95,7 +95,7 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE ListSink @@ -2132,7 +2132,7 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/print_header.q.out b/ql/src/test/results/clientpositive/print_header.q.out index f01d1d3..a8848e7 100644 --- a/ql/src/test/results/clientpositive/print_header.q.out +++ b/ql/src/test/results/clientpositive/print_header.q.out @@ -38,7 +38,7 @@ POSTHOOK: query: SELECT src.key, sum(substr(src.value,5)) FROM src GROUP BY src. POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -src.key c1 +$f0 $f1 0 0.0 10 10.0 100 200.0 diff --git a/ql/src/test/results/clientpositive/ptf.q.out b/ql/src/test/results/clientpositive/ptf.q.out index 9d34e4e..6c75409 100644 --- a/ql/src/test/results/clientpositive/ptf.q.out +++ b/ql/src/test/results/clientpositive/ptf.q.out @@ -241,12 +241,16 @@ STAGE PLANS: 1 p_partkey (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col1 (type: string), _col2 (type: string), _col5 (type: int) + outputColumnNames: _col1, _col2, _col5 + Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -945,52 +949,56 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string, _col2: int - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col1 - partition by: _col0 - raw input shape: - window functions: - window function definition - alias: rank_window_0 - arguments: _col1 - name: rank - window function: GenericUDAFRankEvaluator - window frame: PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true - window function definition - alias: dense_rank_window_1 - arguments: _col1 - name: dense_rank - window function: GenericUDAFDenseRankEvaluator - window frame: PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true - window function definition - alias: lag_window_2 - arguments: _col2, 1, _col2 - name: lag - window function: GenericUDAFLagEvaluator - window frame: PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), _col2 (type: int), (_col2 - lag_window_2) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string, _col2: int + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col1 + partition by: _col0 + raw input shape: + window functions: + window function definition + alias: rank_window_0 + arguments: _col1 + name: rank + window function: GenericUDAFRankEvaluator + window frame: PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true + window function definition + alias: dense_rank_window_1 + arguments: _col1 + name: dense_rank + window function: GenericUDAFDenseRankEvaluator + window frame: PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true + window function definition + alias: lag_window_2 + arguments: _col2, 1, _col2 + name: lag + window function: GenericUDAFLagEvaluator + window frame: PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), _col2 (type: int), (_col2 - lag_window_2) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1140,13 +1148,17 @@ STAGE PLANS: 1 p_partkey (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2656,13 +2668,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2780,26 +2796,30 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: mfgr_price_view - output shape: _col0: string, _col1: string, _col2: double - type: TABLE - Partition table definition - input alias: ptf_1 - name: noop - order by: _col0 - output shape: _col0: string, _col1: string, _col2: double - partition by: _col0 - raw input shape: + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + PTF Operator + Function definitions: + Input definition + input alias: mfgr_price_view + output shape: _col0: string, _col1: string, _col2: double + type: TABLE + Partition table definition + input alias: ptf_1 + name: noop + order by: _col0 + output shape: _col0: string, _col1: string, _col2: double + partition by: _col0 + raw input shape: + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce diff --git a/ql/src/test/results/clientpositive/ptf_decimal.q.out b/ql/src/test/results/clientpositive/ptf_decimal.q.out index 8494e97..75870ed 100644 --- a/ql/src/test/results/clientpositive/ptf_decimal.q.out +++ b/ql/src/test/results/clientpositive/ptf_decimal.q.out @@ -76,32 +76,32 @@ from part POSTHOOK: type: QUERY POSTHOOK: Input: default@part #### A masked pattern was here #### -Manufacturer#1 1173.15 1 1 1 0.0 0.3333333333333333 1 -Manufacturer#1 1173.15 2 1 1 0.0 0.3333333333333333 1 -Manufacturer#1 1414.42 3 3 2 0.4 0.5 2 -Manufacturer#1 1602.59 4 4 3 0.6 0.6666666666666666 3 -Manufacturer#1 1632.66 5 5 4 0.8 0.8333333333333334 4 -Manufacturer#1 1753.76 6 6 5 1.0 1.0 5 -Manufacturer#2 1690.68 1 1 1 0.0 0.2 1 -Manufacturer#2 1698.66 2 2 2 0.25 0.4 2 -Manufacturer#2 1701.6 3 3 3 0.5 0.6 3 -Manufacturer#2 1800.7 4 4 4 0.75 0.8 4 -Manufacturer#2 2031.98 5 5 5 1.0 1.0 5 -Manufacturer#3 1190.27 1 1 1 0.0 0.2 1 -Manufacturer#3 1337.29 2 2 2 0.25 0.4 2 -Manufacturer#3 1410.39 3 3 3 0.5 0.6 3 -Manufacturer#3 1671.68 4 4 4 0.75 0.8 4 -Manufacturer#3 1922.98 5 5 5 1.0 1.0 5 -Manufacturer#4 1206.26 1 1 1 0.0 0.2 1 -Manufacturer#4 1290.35 2 2 2 0.25 0.4 2 -Manufacturer#4 1375.42 3 3 3 0.5 0.6 3 -Manufacturer#4 1620.67 4 4 4 0.75 0.8 4 -Manufacturer#4 1844.92 5 5 5 1.0 1.0 5 -Manufacturer#5 1018.1 1 1 1 0.0 0.2 1 -Manufacturer#5 1464.48 2 2 2 0.25 0.4 2 -Manufacturer#5 1611.66 3 3 3 0.5 0.6 3 -Manufacturer#5 1788.73 4 4 4 0.75 0.8 4 -Manufacturer#5 1789.69 5 5 5 1.0 1.0 5 +Manufacturer#1 1173.15 1 1 1 0.0 0 1 +Manufacturer#1 1173.15 2 1 1 0.0 0 1 +Manufacturer#1 1414.42 3 3 2 0.4 0 2 +Manufacturer#1 1602.59 4 4 3 0.6 0 3 +Manufacturer#1 1632.66 5 5 4 0.8 0 4 +Manufacturer#1 1753.76 6 6 5 1.0 1 5 +Manufacturer#2 1690.68 1 1 1 0.0 0 1 +Manufacturer#2 1698.66 2 2 2 0.25 0 2 +Manufacturer#2 1701.6 3 3 3 0.5 0 3 +Manufacturer#2 1800.7 4 4 4 0.75 0 4 +Manufacturer#2 2031.98 5 5 5 1.0 1 5 +Manufacturer#3 1190.27 1 1 1 0.0 0 1 +Manufacturer#3 1337.29 2 2 2 0.25 0 2 +Manufacturer#3 1410.39 3 3 3 0.5 0 3 +Manufacturer#3 1671.68 4 4 4 0.75 0 4 +Manufacturer#3 1922.98 5 5 5 1.0 1 5 +Manufacturer#4 1206.26 1 1 1 0.0 0 1 +Manufacturer#4 1290.35 2 2 2 0.25 0 2 +Manufacturer#4 1375.42 3 3 3 0.5 0 3 +Manufacturer#4 1620.67 4 4 4 0.75 0 4 +Manufacturer#4 1844.92 5 5 5 1.0 1 5 +Manufacturer#5 1018.1 1 1 1 0.0 0 1 +Manufacturer#5 1464.48 2 2 2 0.25 0 2 +Manufacturer#5 1611.66 3 3 3 0.5 0 3 +Manufacturer#5 1788.73 4 4 4 0.75 0 4 +Manufacturer#5 1789.69 5 5 5 1.0 1 5 PREHOOK: query: -- 3. order by decimal select p_mfgr, p_retailprice, diff --git a/ql/src/test/results/clientpositive/ptf_streaming.q.out b/ql/src/test/results/clientpositive/ptf_streaming.q.out index b4101ea..1b13eee 100644 --- a/ql/src/test/results/clientpositive/ptf_streaming.q.out +++ b/ql/src/test/results/clientpositive/ptf_streaming.q.out @@ -241,12 +241,16 @@ STAGE PLANS: 1 p_partkey (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col1 (type: string), _col2 (type: string), _col5 (type: int) + outputColumnNames: _col1, _col2, _col5 + Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -475,13 +479,17 @@ STAGE PLANS: 1 p_partkey (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/ptfgroupbyjoin.q.out b/ql/src/test/results/clientpositive/ptfgroupbyjoin.q.out index 9368df9..a978751 100644 --- a/ql/src/test/results/clientpositive/ptfgroupbyjoin.q.out +++ b/ql/src/test/results/clientpositive/ptfgroupbyjoin.q.out @@ -96,39 +96,43 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: int, _col1: int - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0, _col1 - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: row_number_window_0 - name: row_number - window function: GenericUDAFRowNumberEvaluator - window frame: PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col1 is not null (type: boolean) + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: int, _col1: int + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0, _col1 + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: row_number_window_0 + name: row_number + window function: GenericUDAFRowNumberEvaluator + window frame: PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int) - outputColumnNames: _col0, _col1 + Filter Operator + predicate: _col1 is not null (type: boolean) Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -253,39 +257,43 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: int, _col1: int - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0, _col1 - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: row_number_window_0 - name: row_number - window function: GenericUDAFRowNumberEvaluator - window frame: PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col1 is not null (type: boolean) + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: int, _col1: int + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0, _col1 + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: row_number_window_0 + name: row_number + window function: GenericUDAFRowNumberEvaluator + window frame: PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), row_number_window_0 (type: int) - outputColumnNames: _col0, _col1, _col2 + Filter Operator + predicate: _col1 is not null (type: boolean) Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: int), row_number_window_0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -410,39 +418,43 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: int, _col1: int - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0, _col1 - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: row_number_window_0 - name: row_number - window function: GenericUDAFRowNumberEvaluator - window frame: PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int) - outputColumnNames: _col0, _col1 + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: int, _col1: int + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0, _col1 + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: row_number_window_0 + name: row_number + window function: GenericUDAFRowNumberEvaluator + window frame: PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col1 is not null (type: boolean) + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Filter Operator + predicate: _col1 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce diff --git a/ql/src/test/results/clientpositive/push_or.q.out b/ql/src/test/results/clientpositive/push_or.q.out index 28446c5..a1d30f7 100644 --- a/ql/src/test/results/clientpositive/push_or.q.out +++ b/ql/src/test/results/clientpositive/push_or.q.out @@ -92,14 +92,14 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col2 (type: string) + key expressions: key (type: int), ds (type: string) sort order: ++ Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) + tag: 0 + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -200,8 +200,8 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: KEY.reducesinkkey0 (type: int), VALUE.value (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -214,7 +214,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2 + columns key,value,ds columns.types int:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true diff --git a/ql/src/test/results/clientpositive/query_result_fileformat.q.out b/ql/src/test/results/clientpositive/query_result_fileformat.q.out index 71a50dd..96cf3b5 100644 --- a/ql/src/test/results/clientpositive/query_result_fileformat.q.out +++ b/ql/src/test/results/clientpositive/query_result_fileformat.q.out @@ -57,7 +57,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'key1' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -128,7 +128,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'key1' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/quote1.q.out b/ql/src/test/results/clientpositive/quote1.q.out index f8592c4..e97e06e 100644 --- a/ql/src/test/results/clientpositive/quote1.q.out +++ b/ql/src/test/results/clientpositive/quote1.q.out @@ -123,7 +123,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: location (type: int), type (type: string), '2008-04-08' (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: location, type, table Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/quote2.q.out b/ql/src/test/results/clientpositive/quote2.q.out index 086960a..df84936 100644 --- a/ql/src/test/results/clientpositive/quote2.q.out +++ b/ql/src/test/results/clientpositive/quote2.q.out @@ -43,7 +43,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'abc' (type: string), 'abc' (type: string), 'abc'' (type: string), 'abc"' (type: string), 'abc\' (type: string), 'abc\' (type: string), 'abc\'' (type: string), 'abc\"' (type: string), 'abc\\' (type: string), 'abc\\' (type: string), 'abc\\'' (type: string), 'abc\\"' (type: string), 'abc\\\' (type: string), 'abc\\\' (type: string), 'abc""""\' (type: string), 'abc''''\' (type: string), 'mysql_%\_\%' (type: string), 'mysql\\_\\\%' (type: string), 'awk '{print NR"\t"$0}'' (type: string), 'tab tab' (type: string), 'tab tab' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20 Statistics: Num rows: 500 Data size: 952500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 diff --git a/ql/src/test/results/clientpositive/quotedid_basic.q.out b/ql/src/test/results/clientpositive/quotedid_basic.q.out index 50c83a8..fc59395 100644 --- a/ql/src/test/results/clientpositive/quotedid_basic.q.out +++ b/ql/src/test/results/clientpositive/quotedid_basic.q.out @@ -42,7 +42,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: x+1 (type: string), y&y (type: string), !@#$%^&*()_q (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: x+1, y&y, !@#$%^&*()_q Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE ListSink @@ -66,7 +66,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: x+1 (type: string), y&y (type: string), '1' (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: x+1, y&y, !@#$%^&*()_q Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false @@ -102,10 +102,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: x+1 (type: string), y&y (type: string), '1' (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: x+1, y&y, !@#$%^&*()_q Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) + keys: x+1 (type: string), y&y (type: string), !@#$%^&*()_q (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -118,15 +118,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: x+1, y&y, !@#$%^&*()_q Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: x+1 (type: string), y&y (type: string), !@#$%^&*()_q (type: string) + outputColumnNames: x+1, y&y, !@#$%^&*()_q Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -157,10 +161,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: x+1 (type: string), y&y (type: string), '1' (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: x+1, y&y, !@#$%^&*()_q Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) + keys: x+1 (type: string), y&y (type: string), !@#$%^&*()_q (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -173,7 +177,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: x+1, y&y, !@#$%^&*()_q Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false @@ -187,40 +191,40 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col2 (type: string), _col1 (type: string) + key expressions: !@#$%^&*()_q (type: string), y&y (type: string) sort order: ++ - Map-reduce partition columns: _col2 (type: string) + Map-reduce partition columns: !@#$%^&*()_q (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: string) + value expressions: x+1 (type: string) Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: VALUE.x+1 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string) + outputColumnNames: x+1, y&y, !@#$%^&*()_q Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col0: string, _col1: string, _col2: string + output shape: x+1: string, y&y: string, !@#$%^&*()_q: string type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col1 - partition by: _col2 + order by: y&y + partition by: !@#$%^&*()_q raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col1 + alias: $win$_col_26 + arguments: y&y name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), rank_window_0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: x+1 (type: string), y&y (type: string), !@#$%^&*()_q (type: string), $win$_col_26 (type: int) + outputColumnNames: (tok_table_or_col x+1), (tok_table_or_col y&y), (tok_table_or_col !@#$%^&*()_q), rank_window_0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false @@ -261,10 +265,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: x+1 (type: string), y&y (type: string), '1' (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: x+1, y&y, !@#$%^&*()_q Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) + keys: x+1 (type: string), y&y (type: string), !@#$%^&*()_q (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -277,7 +281,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: x+1, y&y, !@#$%^&*()_q Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false @@ -291,40 +295,40 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col2 (type: string), _col1 (type: string) + key expressions: !@#$%^&*()_q (type: string), y&y (type: string) sort order: ++ - Map-reduce partition columns: _col2 (type: string) + Map-reduce partition columns: !@#$%^&*()_q (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: string) + value expressions: x+1 (type: string) Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: VALUE.x+1 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string) + outputColumnNames: x+1, y&y, !@#$%^&*()_q Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col0: string, _col1: string, _col2: string + output shape: x+1: string, y&y: string, !@#$%^&*()_q: string type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col1 - partition by: _col2 + order by: y&y + partition by: !@#$%^&*()_q raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col1 + alias: $win$_col_27 + arguments: y&y name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), rank_window_0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: x+1 (type: string), y&y (type: string), !@#$%^&*()_q (type: string), $win$_col_27 (type: int) + outputColumnNames: (tok_table_or_col x+1), (tok_table_or_col y&y), (tok_table_or_col !@#$%^&*()_q), rank_window_0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/quotedid_partition.q.out b/ql/src/test/results/clientpositive/quotedid_partition.q.out index bc52c82..259596d 100644 --- a/ql/src/test/results/clientpositive/quotedid_partition.q.out +++ b/ql/src/test/results/clientpositive/quotedid_partition.q.out @@ -47,10 +47,10 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '10' (type: string), y&y (type: string), 'a' (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: x+1, y&y, !@#$%^&*()_q Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) + keys: x+1 (type: string), y&y (type: string), !@#$%^&*()_q (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -63,15 +63,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: x+1, y&y, !@#$%^&*()_q Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: x+1 (type: string), y&y (type: string), !@#$%^&*()_q (type: string) + outputColumnNames: x+1, y&y, !@#$%^&*()_q Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/quotedid_skew.q.out b/ql/src/test/results/clientpositive/quotedid_skew.q.out index 9ac2b62..a1acf5f 100644 --- a/ql/src/test/results/clientpositive/quotedid_skew.q.out +++ b/ql/src/test/results/clientpositive/quotedid_skew.q.out @@ -106,23 +106,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce diff --git a/ql/src/test/results/clientpositive/rand_partitionpruner1.q.out b/ql/src/test/results/clientpositive/rand_partitionpruner1.q.out index 90f17a7..224f32d 100644 --- a/ql/src/test/results/clientpositive/rand_partitionpruner1.q.out +++ b/ql/src/test/results/clientpositive/rand_partitionpruner1.q.out @@ -38,35 +38,39 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (rand(1) < 0.1) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + isSamplingPred: false + predicate: (rand(1) < 0.1) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1 - columns.types string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns key,value + columns.types string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: diff --git a/ql/src/test/results/clientpositive/rand_partitionpruner2.q.out b/ql/src/test/results/clientpositive/rand_partitionpruner2.q.out index d04ad8b..ad61451 100644 --- a/ql/src/test/results/clientpositive/rand_partitionpruner2.q.out +++ b/ql/src/test/results/clientpositive/rand_partitionpruner2.q.out @@ -67,42 +67,46 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (rand(1) < 0.1) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Filter Operator + isSamplingPred: false + predicate: ((rand(1) < 0.1) and (ds = '2008-04-08')) (type: boolean) Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) + outputColumnNames: key, value, ds, hr Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value,hr,ds - columns.comments - columns.types string:string:string:string -#### A masked pattern was here #### - name default.tmptable - serialization.ddl struct tmptable { string key, string value, string hr, string ds} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmptable - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value,hr,ds + columns.comments + columns.types string:string:string:string +#### A masked pattern was here #### + name default.tmptable + serialization.ddl struct tmptable { string key, string value, string hr, string ds} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmptable + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -198,9 +202,103 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 11 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 12 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart Truncated Path -> Alias: /srcpart/ds=2008-04-08/hr=11 [a] /srcpart/ds=2008-04-08/hr=12 [a] + /srcpart/ds=2008-04-09/hr=11 [a] + /srcpart/ds=2008-04-09/hr=12 [a] Stage: Stage-7 Conditional Operator @@ -387,6 +485,8 @@ PREHOOK: type: QUERY PREHOOK: Input: default@srcpart PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 PREHOOK: Output: default@tmptable POSTHOOK: query: insert overwrite table tmptable select a.* from srcpart a where rand(1) < 0.1 and a.ds = '2008-04-08' @@ -394,6 +494,8 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 POSTHOOK: Output: default@tmptable POSTHOOK: Lineage: tmptable.ds SIMPLE [(srcpart)a.FieldSchema(name:hr, type:string, comment:null), ] POSTHOOK: Lineage: tmptable.hr SIMPLE [(srcpart)a.FieldSchema(name:ds, type:string, comment:null), ] diff --git a/ql/src/test/results/clientpositive/rand_partitionpruner3.q.out b/ql/src/test/results/clientpositive/rand_partitionpruner3.q.out index 634e171..48cc19c 100644 --- a/ql/src/test/results/clientpositive/rand_partitionpruner3.q.out +++ b/ql/src/test/results/clientpositive/rand_partitionpruner3.q.out @@ -69,6 +69,138 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Partition + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Partition + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 11 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Partition + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 hr 12 properties: COLUMN_STATS_ACCURATE true @@ -111,33 +243,41 @@ STAGE PLANS: Processor Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((rand(1) < 0.1) and ((UDFToDouble(key) <= 50.0) and (UDFToDouble(key) >= 10.0))) (type: boolean) - Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Filter Operator + isSamplingPred: false + predicate: ((rand(1) < 0.1) and (ds = '2008-04-08') and ((UDFToDouble(key) <= 50.0) and (UDFToDouble(key) >= 10.0)) and (hr like '%2')) (type: boolean) Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE - ListSink + Select Operator + expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE + ListSink PREHOOK: query: select a.* from srcpart a where rand(1) < 0.1 and a.ds = '2008-04-08' and not(key > 50 or key < 10) and a.hr like '%2' PREHOOK: type: QUERY PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### POSTHOOK: query: select a.* from srcpart a where rand(1) < 0.1 and a.ds = '2008-04-08' and not(key > 50 or key < 10) and a.hr like '%2' POSTHOOK: type: QUERY POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### -42 val_42 2008-04-08 12 -44 val_44 2008-04-08 12 -26 val_26 2008-04-08 12 +47 val_47 2008-04-08 12 +35 val_35 2008-04-08 12 18 val_18 2008-04-08 12 -37 val_37 2008-04-08 12 PREHOOK: query: -- without rand for comparison explain extended select a.* from srcpart a where a.ds = '2008-04-08' and not(key > 50 or key < 10) and a.hr like '%2' PREHOOK: type: QUERY @@ -251,7 +391,7 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/rcfile_createas1.q.out b/ql/src/test/results/clientpositive/rcfile_createas1.q.out index 97eaa1a..c45c7bd 100644 --- a/ql/src/test/results/clientpositive/rcfile_createas1.q.out +++ b/ql/src/test/results/clientpositive/rcfile_createas1.q.out @@ -72,7 +72,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), (hash(key) pmod 50) (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, part Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/rcfile_merge3.q.out b/ql/src/test/results/clientpositive/rcfile_merge3.q.out index 1566ec3..faafd9e 100644 --- a/ql/src/test/results/clientpositive/rcfile_merge3.q.out +++ b/ql/src/test/results/clientpositive/rcfile_merge3.q.out @@ -73,7 +73,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/rcfile_merge4.q.out b/ql/src/test/results/clientpositive/rcfile_merge4.q.out index 6171434..7ddc786 100644 --- a/ql/src/test/results/clientpositive/rcfile_merge4.q.out +++ b/ql/src/test/results/clientpositive/rcfile_merge4.q.out @@ -73,7 +73,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/rcfile_null_value.q.out b/ql/src/test/results/clientpositive/rcfile_null_value.q.out index c90287c..0b7ce65 100644 --- a/ql/src/test/results/clientpositive/rcfile_null_value.q.out +++ b/ql/src/test/results/clientpositive/rcfile_null_value.q.out @@ -97,48 +97,48 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: c:a:src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 15.0)) and (UDFToDouble(key) < 25.0)) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src1 + alias: c:b:src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string), UDFToInteger(key0) (type: int), value0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -195,10 +195,10 @@ INSERT OVERWRITE TABLE dest1_rc SELECT c.c1, c.c2, c.c3, c.c4 POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1_rc -POSTHOOK: Lineage: dest1_rc.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1_rc.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1_rc.c3 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1_rc.c4 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1_rc.c1 EXPRESSION [(src)c:a:src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1_rc.c2 SIMPLE [(src)c:a:src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1_rc.c3 EXPRESSION [(src)c:b:src2.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1_rc.c4 SIMPLE [(src)c:b:src2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest1_rc.* FROM dest1_rc PREHOOK: type: QUERY PREHOOK: Input: default@dest1_rc diff --git a/ql/src/test/results/clientpositive/reduce_deduplicate_exclude_join.q.out b/ql/src/test/results/clientpositive/reduce_deduplicate_exclude_join.q.out index bc1eeb3..ad6fa9c 100644 --- a/ql/src/test/results/clientpositive/reduce_deduplicate_exclude_join.q.out +++ b/ql/src/test/results/clientpositive/reduce_deduplicate_exclude_join.q.out @@ -71,16 +71,20 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 1 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/reduce_deduplicate_extended.q.out b/ql/src/test/results/clientpositive/reduce_deduplicate_extended.q.out index df16ab2..9b7e0d9 100644 --- a/ql/src/test/results/clientpositive/reduce_deduplicate_extended.q.out +++ b/ql/src/test/results/clientpositive/reduce_deduplicate_extended.q.out @@ -43,13 +43,17 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -70,32 +74,32 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: q1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), lower(_col1) (type: string) + key expressions: key (type: string), lower(value) (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), lower(_col1) (type: string) + Map-reduce partition columns: key (type: string), lower(value) (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), lower(VALUE._col0) (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), lower(VALUE.value) (type: string) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) - keys: _col0 (type: string), _col1 (type: string) + aggregations: sum($f0) + keys: $f0 (type: string), $f1 (type: string) mode: complete - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: double), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f2 (type: double), $f1 (type: string) + outputColumnNames: key, _o__c1, _o__c2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -124,32 +128,32 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: q1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), (UDFToDouble(value) + 1.0) (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: key, x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), (_col1 + 1.0) (type: double) + key expressions: key (type: string), (x + 1.0) (type: double) sort order: ++ - Map-reduce partition columns: _col0 (type: string), (_col1 + 1.0) (type: double) + Map-reduce partition columns: key (type: string), (x + 1.0) (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double) + value expressions: x (type: double) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), (VALUE._col0 + 1.0) (type: double) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), (VALUE.x + 1.0) (type: double) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) - keys: _col0 (type: string), _col1 (type: double) + aggregations: sum($f0) + keys: $f0 (type: string), $f1 (type: double) mode: complete - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: double), _col1 (type: double) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f2 (type: double), $f1 (type: double) + outputColumnNames: key, _o__c1, _o__c2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -184,11 +188,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) - keys: _col0 (type: string) + aggregations: sum(key) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -203,15 +207,19 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: double) + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -242,14 +250,14 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan alias: src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -258,34 +266,38 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: sum($f0) + keys: $f0 (type: string), $f1 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -302,11 +314,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: double) - outputColumnNames: _col0, _col1 + expressions: $f0 (type: string), $f2 (type: double) + outputColumnNames: key, _o__c1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -345,14 +357,14 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan alias: src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -361,41 +373,45 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -426,14 +442,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: s:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -446,24 +462,28 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: key (type: string) + outputColumnNames: $f0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: $f0 (type: string) mode: complete - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string) + outputColumnNames: $f0 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -484,14 +504,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: t:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -504,17 +524,17 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string) + aggregations: count(DISTINCT value) + keys: key (type: string) mode: complete - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, $f1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2541,13 +2561,17 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2568,32 +2592,32 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: q1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), lower(_col1) (type: string) + key expressions: key (type: string), lower(value) (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), lower(_col1) (type: string) + Map-reduce partition columns: key (type: string), lower(value) (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), lower(VALUE._col0) (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), lower(VALUE.value) (type: string) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) - keys: _col0 (type: string), _col1 (type: string) + aggregations: sum($f0) + keys: $f0 (type: string), $f1 (type: string) mode: complete - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: double), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f2 (type: double), $f1 (type: string) + outputColumnNames: key, _o__c1, _o__c2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2622,32 +2646,32 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: q1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), (UDFToDouble(value) + 1.0) (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: key, x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), (_col1 + 1.0) (type: double) + key expressions: key (type: string), (x + 1.0) (type: double) sort order: ++ - Map-reduce partition columns: _col0 (type: string), (_col1 + 1.0) (type: double) + Map-reduce partition columns: key (type: string), (x + 1.0) (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double) + value expressions: x (type: double) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), (VALUE._col0 + 1.0) (type: double) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), (VALUE.x + 1.0) (type: double) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) - keys: _col0 (type: string), _col1 (type: double) + aggregations: sum($f0) + keys: $f0 (type: string), $f1 (type: double) mode: complete - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: double), _col1 (type: double) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f2 (type: double), $f1 (type: double) + outputColumnNames: key, _o__c1, _o__c2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2682,27 +2706,32 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: string) Reduce Operator Tree: Group By Operator - aggregations: sum(KEY._col0) + aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: complete - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: double) + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2733,14 +2762,14 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan alias: src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -2749,48 +2778,53 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: $f0 (type: string), $f1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: $f0 (type: string), $f1 (type: string) Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions: $f0 (type: string) Reduce Operator Tree: Group By Operator - aggregations: sum(KEY._col0) + aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: double) - outputColumnNames: _col0, _col1 + expressions: $f0 (type: string), $f2 (type: double) + outputColumnNames: key, _o__c1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2829,14 +2863,14 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan alias: src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -2845,41 +2879,45 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2910,39 +2948,43 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: s:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: key (type: string) + outputColumnNames: $f0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: $f0 (type: string) mode: complete - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string) + outputColumnNames: $f0 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2963,36 +3005,40 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: t:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string) + aggregations: count(DISTINCT value) + keys: key (type: string) mode: complete - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, $f1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/regex_col.q.out b/ql/src/test/results/clientpositive/regex_col.q.out index 16f8f88..53c0bf9 100644 --- a/ql/src/test/results/clientpositive/regex_col.q.out +++ b/ql/src/test/results/clientpositive/regex_col.q.out @@ -17,7 +17,7 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE ListSink @@ -40,7 +40,7 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: ds, hr Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE ListSink @@ -63,7 +63,7 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: ds, hr Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE ListSink @@ -87,46 +87,46 @@ STAGE PLANS: alias: a Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and value is not null) (type: boolean) + predicate: (value is not null and key is not null) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: key (type: string), value (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: string), _col3 (type: string) + value expressions: ds (type: string), hr (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and value is not null) (type: boolean) + predicate: (value is not null and key is not null) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: key (type: string), value (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: string), _col3 (type: string) + value expressions: ds (type: string), hr (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col2, _col3, _col6, _col7 + 0 key (type: string), value (type: string) + 1 key (type: string), value (type: string) + outputColumnNames: ds, hr, ds0, hr0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: ds (type: string), hr (type: string), ds0 (type: string), hr0 (type: string) + outputColumnNames: ds, hr, ds1, hr1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -169,40 +169,40 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col1, _col2 + outputColumnNames: ds, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: '103' (type: string), _col2 (type: string), _col1 (type: string) + key expressions: '103' (type: string), hr (type: string), ds (type: string) sort order: +++ - Map-reduce partition columns: '103' (type: string), _col2 (type: string), _col1 (type: string) + Map-reduce partition columns: '103' (type: string), hr (type: string), ds (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE TableScan - alias: a + alias: b Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 103.0) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col1, _col2 + outputColumnNames: ds, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: '103' (type: string), _col2 (type: string), _col1 (type: string) + key expressions: '103' (type: string), hr (type: string), ds (type: string) sort order: +++ - Map-reduce partition columns: '103' (type: string), _col2 (type: string), _col1 (type: string) + Map-reduce partition columns: '103' (type: string), hr (type: string), ds (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string), _col2 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col2 (type: string), _col1 (type: string) - outputColumnNames: _col4, _col5 + 0 key (type: string), hr (type: string), ds (type: string) + 1 key (type: string), hr (type: string), ds (type: string) + outputColumnNames: ds0, hr0 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col4 (type: string), _col5 (type: string) - outputColumnNames: _col0, _col1 + expressions: ds0 (type: string), hr0 (type: string) + outputColumnNames: ds, hr Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -216,13 +216,13 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: ds (type: string), hr (type: string) sort order: ++ Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: ds, hr Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -293,7 +293,7 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE ListSink @@ -316,7 +316,7 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE ListSink @@ -339,7 +339,7 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, hr Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE ListSink @@ -362,16 +362,16 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 diff --git a/ql/src/test/results/clientpositive/router_join_ppr.q.out b/ql/src/test/results/clientpositive/router_join_ppr.q.out index b7d593f..264ec9a 100644 --- a/ql/src/test/results/clientpositive/router_join_ppr.q.out +++ b/ql/src/test/results/clientpositive/router_join_ppr.q.out @@ -122,15 +122,15 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false TableScan alias: b @@ -142,15 +142,15 @@ STAGE PLANS: Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string), _col2 (type: string) + value expressions: value (type: string), ds (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -384,11 +384,11 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b] - /srcpart/ds=2008-04-09/hr=11 [$hdt$_1:b] - /srcpart/ds=2008-04-09/hr=12 [$hdt$_1:b] + /src [a] + /srcpart/ds=2008-04-08/hr=11 [b] + /srcpart/ds=2008-04-08/hr=12 [b] + /srcpart/ds=2008-04-09/hr=11 [b] + /srcpart/ds=2008-04-09/hr=12 [b] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -398,37 +398,41 @@ STAGE PLANS: 1 [0, 1] filter predicates: 0 - 1 {(VALUE._col1 = '2008-04-08')} + 1 {(VALUE.ds = '2008-04-08')} keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 244 Data size: 2593 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean) + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns key,value,key0,value0 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -598,15 +602,15 @@ STAGE PLANS: Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false TableScan alias: b @@ -618,15 +622,15 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -768,26 +772,26 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:$hdt$_0:a] + /src [b] + /srcpart/ds=2008-04-08/hr=11 [a] + /srcpart/ds=2008-04-08/hr=12 [a] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3, _col4 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean) + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -800,7 +804,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2,_col3 + columns key,value,key0,value0 columns.types string:string:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true @@ -975,15 +979,15 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false TableScan alias: b @@ -995,15 +999,15 @@ STAGE PLANS: Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -1145,44 +1149,48 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b] + /src [a] + /srcpart/ds=2008-04-08/hr=11 [b] + /srcpart/ds=2008-04-08/hr=12 [b] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Right Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean) + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns key,value,key0,value0 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -1344,19 +1352,19 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: (((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 15.0)) and (UDFToDouble(key) < 25.0)) and key is not null) (type: boolean) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + predicate: ((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 15.0)) and (UDFToDouble(key) < 25.0)) (type: boolean) + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false TableScan alias: b @@ -1364,19 +1372,19 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + predicate: ((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) (type: boolean) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string) + value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -1518,35 +1526,35 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [$hdt$_1:$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:$hdt$_0:a] + /src [b] + /srcpart/ds=2008-04-08/hr=11 [a] + /srcpart/ds=2008-04-08/hr=12 [a] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key1, value1 + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2,_col3 + columns key,value,key1,value1 columns.types string:string:string:string escape.delim \ hive.serialization.extend.additional.nesting.levels true diff --git a/ql/src/test/results/clientpositive/runtime_skewjoin_mapjoin_spark.q.out b/ql/src/test/results/clientpositive/runtime_skewjoin_mapjoin_spark.q.out index cdd5fd9..222d7ca 100644 --- a/ql/src/test/results/clientpositive/runtime_skewjoin_mapjoin_spark.q.out +++ b/ql/src/test/results/clientpositive/runtime_skewjoin_mapjoin_spark.q.out @@ -98,17 +98,19 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -139,17 +141,19 @@ STAGE PLANS: keys: 0 reducesinkkey0 (type: string) 1 reducesinkkey0 (type: string) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -167,13 +171,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-28 Map Reduce Local Work @@ -200,17 +208,19 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -238,17 +248,19 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-21 Conditional Operator @@ -289,12 +301,16 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -326,12 +342,16 @@ STAGE PLANS: 0 reducesinkkey0 (type: string) 1 reducesinkkey0 (type: string) outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -363,17 +383,19 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -402,17 +424,19 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -452,12 +476,16 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -496,12 +524,16 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-24 Conditional Operator @@ -531,17 +563,19 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -570,17 +604,19 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -620,12 +656,16 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -657,12 +697,16 @@ STAGE PLANS: 0 reducesinkkey0 (type: string) 1 reducesinkkey0 (type: string) outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/sample10.q.out b/ql/src/test/results/clientpositive/sample10.q.out index a6bc91a..10a1765 100644 --- a/ql/src/test/results/clientpositive/sample10.q.out +++ b/ql/src/test/results/clientpositive/sample10.q.out @@ -325,23 +325,27 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 60 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1 - columns.types string,bigint - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10 Data size: 60 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1 + columns.types string,bigint + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce diff --git a/ql/src/test/results/clientpositive/script_pipe.q.out b/ql/src/test/results/clientpositive/script_pipe.q.out index e19fc06..cde37a6 100644 --- a/ql/src/test/results/clientpositive/script_pipe.q.out +++ b/ql/src/test/results/clientpositive/script_pipe.q.out @@ -34,20 +34,24 @@ STAGE PLANS: Limit Number of rows: 1 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Transform Operator - command: true - output info: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - table: + Transform Operator + command: true + output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/selectDistinctStar.q.out b/ql/src/test/results/clientpositive/selectDistinctStar.q.out index abd6795..898ad98 100644 --- a/ql/src/test/results/clientpositive/selectDistinctStar.q.out +++ b/ql/src/test/results/clientpositive/selectDistinctStar.q.out @@ -19,10 +19,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -35,15 +35,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -709,10 +713,10 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -725,15 +729,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -920,16 +928,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: null-subquery1:subq-subquery1:src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE @@ -939,16 +947,16 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src + alias: null-subquery2:subq-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE @@ -961,15 +969,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2449,10 +2461,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -2465,15 +2477,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -3135,10 +3151,10 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -3151,15 +3167,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -3346,16 +3366,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: null-subquery1:subq-subquery1:src1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE @@ -3365,16 +3385,16 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src + alias: null-subquery2:subq-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE @@ -3387,15 +3407,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/select_as_omitted.q.out b/ql/src/test/results/clientpositive/select_as_omitted.q.out index de9be1f..6f27c67 100644 --- a/ql/src/test/results/clientpositive/select_as_omitted.q.out +++ b/ql/src/test/results/clientpositive/select_as_omitted.q.out @@ -21,21 +21,21 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 diff --git a/ql/src/test/results/clientpositive/select_transform_hint.q.out b/ql/src/test/results/clientpositive/select_transform_hint.q.out index 43b1ada..a10921a 100644 --- a/ql/src/test/results/clientpositive/select_transform_hint.q.out +++ b/ql/src/test/results/clientpositive/select_transform_hint.q.out @@ -52,20 +52,24 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Transform Operator - command: cat - output info: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: + Transform Operator + command: cat + output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -1171,20 +1175,24 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Transform Operator - command: cat - output info: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: + Transform Operator + command: cat + output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/select_unquote_and.q.out b/ql/src/test/results/clientpositive/select_unquote_and.q.out index 03ad48d..ff79dcb 100644 --- a/ql/src/test/results/clientpositive/select_unquote_and.q.out +++ b/ql/src/test/results/clientpositive/select_unquote_and.q.out @@ -63,7 +63,7 @@ STAGE PLANS: Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/select_unquote_not.q.out b/ql/src/test/results/clientpositive/select_unquote_not.q.out index 3b8146b..8ae6d44 100644 --- a/ql/src/test/results/clientpositive/select_unquote_not.q.out +++ b/ql/src/test/results/clientpositive/select_unquote_not.q.out @@ -63,7 +63,7 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/select_unquote_or.q.out b/ql/src/test/results/clientpositive/select_unquote_or.q.out index de91313..7f12782 100644 --- a/ql/src/test/results/clientpositive/select_unquote_or.q.out +++ b/ql/src/test/results/clientpositive/select_unquote_or.q.out @@ -63,7 +63,7 @@ STAGE PLANS: Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/semijoin.q.out b/ql/src/test/results/clientpositive/semijoin.q.out index 0df96c0..b128734 100644 --- a/ql/src/test/results/clientpositive/semijoin.q.out +++ b/ql/src/test/results/clientpositive/semijoin.q.out @@ -172,12 +172,16 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 47 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 47 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -276,12 +280,16 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 49 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 49 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -382,12 +390,16 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 47 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 47 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -457,16 +469,20 @@ STAGE PLANS: Filter Operator predicate: (key < 15) (type: boolean) Statistics: Num rows: 7 Data size: 51 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: key (type: int), key (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: int) + outputColumnNames: key Statistics: Num rows: 7 Data size: 51 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) + Group By Operator + keys: key (type: int), key (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 7 Data size: 51 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 7 Data size: 51 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -589,12 +605,16 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 47 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 47 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -897,12 +917,16 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 49 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 49 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1001,10 +1025,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 89 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 89 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 12 Data size: 89 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1109,12 +1137,16 @@ STAGE PLANS: 1 (2 * _col0) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 47 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 47 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1343,12 +1375,16 @@ STAGE PLANS: 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1483,10 +1519,14 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 24 Data size: 178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 24 Data size: 178 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 24 Data size: 178 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1591,12 +1631,16 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 358 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 48 Data size: 358 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1720,12 +1764,16 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 358 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 48 Data size: 358 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1852,12 +1900,16 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 358 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 48 Data size: 358 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1984,12 +2036,16 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 358 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 48 Data size: 358 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -2116,12 +2172,16 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 358 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 48 Data size: 358 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -2250,12 +2310,16 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 358 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 48 Data size: 358 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -2427,12 +2491,16 @@ STAGE PLANS: 1 value (type: string) outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 97 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 97 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -2524,18 +2592,18 @@ STAGE PLANS: alias: a Statistics: Num rows: 22 Data size: 163 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > 100) and value is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 29 Basic stats: COMPLETE Column stats: NONE + predicate: (value is not null and (key > 100)) (type: boolean) + Statistics: Num rows: 3 Data size: 22 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 29 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 3 Data size: 22 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 4 Data size: 29 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 3 Data size: 22 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: int) TableScan alias: b Statistics: Num rows: 11 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -2544,34 +2612,33 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key Statistics: Num rows: 6 Data size: 49 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: int) + outputColumnNames: key Statistics: Num rows: 6 Data size: 49 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 49 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/serde_user_properties.q.out b/ql/src/test/results/clientpositive/serde_user_properties.q.out index ac3c135..86b3f67 100644 --- a/ql/src/test/results/clientpositive/serde_user_properties.q.out +++ b/ql/src/test/results/clientpositive/serde_user_properties.q.out @@ -37,7 +37,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink @@ -79,7 +79,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink @@ -247,7 +247,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink @@ -422,7 +422,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/set_processor_namespaces.q.out b/ql/src/test/results/clientpositive/set_processor_namespaces.q.out index 3c67727..8aa87c4 100644 --- a/ql/src/test/results/clientpositive/set_processor_namespaces.q.out +++ b/ql/src/test/results/clientpositive/set_processor_namespaces.q.out @@ -23,7 +23,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '5' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/set_variable_sub.q.out b/ql/src/test/results/clientpositive/set_variable_sub.q.out index c72da07..b393e5e 100644 --- a/ql/src/test/results/clientpositive/set_variable_sub.q.out +++ b/ql/src/test/results/clientpositive/set_variable_sub.q.out @@ -18,7 +18,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'value1' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -54,7 +54,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'value1' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -90,7 +90,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '1' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/skewjoin.q.out b/ql/src/test/results/clientpositive/skewjoin.q.out index 22a9421..fbe8b99 100644 --- a/ql/src/test/results/clientpositive/skewjoin.q.out +++ b/ql/src/test/results/clientpositive/skewjoin.q.out @@ -95,21 +95,21 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src1 + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -118,12 +118,12 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator @@ -131,12 +131,12 @@ STAGE PLANS: Inner Join 0 to 1 handleSkewJoin: true keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col2) (type: int), _col1 (type: string) + expressions: UDFToInteger(key0) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -175,9 +175,9 @@ STAGE PLANS: keys: 0 reducesinkkey0 (type: string) 1 reducesinkkey0 (type: string) - outputColumnNames: _col1, _col2 + outputColumnNames: value, key0 Select Operator - expressions: UDFToInteger(_col2) (type: int), _col1 (type: string) + expressions: UDFToInteger(key0) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -215,7 +215,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest_j1 POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT sum(hash(key)), sum(hash(value)) FROM dest_j1 PREHOOK: type: QUERY PREHOOK: Input: default@dest_j1 @@ -511,17 +511,21 @@ STAGE PLANS: 1 (key + 1) (type: double) outputColumnNames: _col0, _col1, _col5 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col5)) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string) + outputColumnNames: _col0, _col1, _col5 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col5)) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -537,13 +541,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -589,35 +597,35 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: y:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src + alias: x:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator @@ -625,16 +633,16 @@ STAGE PLANS: Inner Join 0 to 1 handleSkewJoin: true keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash(key) (type: int), hash(value) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -672,13 +680,13 @@ STAGE PLANS: keys: 0 reducesinkkey0 (type: string) 1 reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Select Operator - expressions: hash(_col0) (type: int), hash(_col1) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash(key) (type: int), hash(value) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -703,15 +711,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -765,52 +777,52 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: x:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(substring(value, 5)) is not null) (type: boolean) + predicate: (value is not null and key is not null) (type: boolean) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double) + key expressions: key (type: string), UDFToDouble(substring(value, 5)) (type: double) sort order: ++ - Map-reduce partition columns: _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double) + Map-reduce partition columns: key (type: string), UDFToDouble(substring(value, 5)) (type: double) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src + alias: y:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and (UDFToDouble(substring(value, 5)) + 1.0) is not null) (type: boolean) + predicate: (value is not null and key is not null) (type: boolean) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + 1.0) (type: double) + key expressions: key (type: string), (UDFToDouble(substring(value, 5)) + UDFToDouble(1)) (type: double) sort order: ++ - Map-reduce partition columns: _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + 1.0) (type: double) + Map-reduce partition columns: key (type: string), (UDFToDouble(substring(value, 5)) + UDFToDouble(1)) (type: double) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 handleSkewJoin: true keys: - 0 _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double) - 1 _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + 1.0) (type: double) - outputColumnNames: _col2, _col3 + 0 key (type: string), UDFToDouble(substring(value, 5)) (type: double) + 1 key (type: string), (UDFToDouble(substring(value, 5)) + UDFToDouble(1)) (type: double) + outputColumnNames: key0, value0 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col2) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash(key0) (type: int), hash(value0) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -848,13 +860,13 @@ STAGE PLANS: keys: 0 reducesinkkey0 (type: string), reducesinkkey1 (type: double) 1 reducesinkkey0 (type: string), reducesinkkey1 (type: double) - outputColumnNames: _col2, _col3 + outputColumnNames: key0, value0 Select Operator - expressions: hash(_col2) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1 + expressions: hash(key0) (type: int), hash(value0) (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -879,15 +891,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -937,73 +953,80 @@ JOIN ON src1.c1 = src3.c5 AND src3.c5 < 80 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-3 is a root stage - Stage-8 depends on stages: Stage-3 , consists of Stage-10, Stage-1 + Stage-1 is a root stage + Stage-9 depends on stages: Stage-1 , consists of Stage-11, Stage-2 + Stage-11 + Stage-8 depends on stages: Stage-11 + Stage-2 depends on stages: Stage-8 + Stage-7 depends on stages: Stage-2 , consists of Stage-10, Stage-3 Stage-10 - Stage-7 depends on stages: Stage-10 - Stage-1 depends on stages: Stage-7 - Stage-6 depends on stages: Stage-1 , consists of Stage-9, Stage-2 - Stage-9 - Stage-5 depends on stages: Stage-9 - Stage-2 depends on stages: Stage-5 - Stage-0 depends on stages: Stage-2 + Stage-6 depends on stages: Stage-10 + Stage-3 depends on stages: Stage-6 + Stage-0 depends on stages: Stage-3 STAGE PLANS: - Stage: Stage-3 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: src + alias: src1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(key) < 100.0) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src + alias: src2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(key) < 100.0) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 handleSkewJoin: true keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean) + Statistics: Num rows: 20 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 20 Data size: 213 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-8 + Stage: Stage-9 Conditional Operator - Stage: Stage-10 + Stage: Stage-11 Map Reduce Local Work Alias -> Map Local Tables: 1 @@ -1017,7 +1040,7 @@ STAGE PLANS: 0 reducesinkkey0 (type: string) 1 reducesinkkey0 (type: string) - Stage: Stage-7 + Stage: Stage-8 Map Reduce Map Operator Tree: TableScan @@ -1027,57 +1050,64 @@ STAGE PLANS: keys: 0 reducesinkkey0 (type: string) 1 reducesinkkey0 (type: string) - outputColumnNames: _col0, _col2 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: key, value + Filter Operator + predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean) + Statistics: Num rows: 20 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 20 Data size: 213 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: src + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 20 Data size: 213 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + TableScan + alias: src3:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 80.0) and (UDFToDouble(key) < 100.0)) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) < 80.0) and (UDFToDouble(key) < 100.0)) (type: boolean) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 handleSkewJoin: true keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col3 - Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hash(_col1) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE + expressions: hash(key) (type: int), hash(value) (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -1088,10 +1118,10 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-6 + Stage: Stage-7 Conditional Operator - Stage: Stage-9 + Stage: Stage-10 Map Reduce Local Work Alias -> Map Local Tables: 1 @@ -1105,7 +1135,7 @@ STAGE PLANS: 0 reducesinkkey0 (type: string) 1 reducesinkkey0 (type: string) - Stage: Stage-5 + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan @@ -1115,13 +1145,13 @@ STAGE PLANS: keys: 0 reducesinkkey0 (type: string) 1 reducesinkkey0 (type: string) - outputColumnNames: _col1, _col3 + outputColumnNames: key, value Select Operator - expressions: hash(_col1) (type: int), hash(_col3) (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE + expressions: hash(key) (type: int), hash(value) (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0), sum(_col1) + aggregations: sum($f0), sum($f1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -1134,7 +1164,7 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-2 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan @@ -1146,15 +1176,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1229,15 +1263,19 @@ STAGE PLANS: 1 UDFToDouble(key) (type: double) outputColumnNames: _col0, _col6 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0)), sum(hash(_col6)) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: _col0 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col6 + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0)), sum(hash(_col6)) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1246,13 +1284,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin1.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin1.q.out index 91d31cd..554d1a9 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin1.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin1.q.out @@ -112,13 +112,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -139,13 +142,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -245,13 +251,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -272,13 +281,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -373,17 +385,22 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Select Operator + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) TableScan alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -397,17 +414,22 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Select Operator + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -416,13 +438,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -502,17 +528,22 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Select Operator + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) TableScan alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -526,17 +557,22 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Select Operator + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -545,13 +581,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out index ca966c2..fba9500 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out @@ -152,13 +152,16 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -179,13 +182,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -285,13 +291,16 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -312,13 +321,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -413,17 +425,22 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Select Operator + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) TableScan alias: b Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -437,17 +454,22 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Select Operator + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -456,13 +478,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -542,17 +568,22 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Select Operator + Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) TableScan alias: b Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -566,17 +597,22 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Select Operator + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -585,13 +621,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin11.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin11.q.out index 51445a5..3c04093 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin11.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin11.q.out @@ -116,13 +116,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -143,13 +146,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin2.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin2.q.out index f3b5526..6e2bd43 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin2.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin2.q.out @@ -116,13 +116,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -143,13 +146,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -247,23 +253,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin3.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin3.q.out index 1902c47..0eeb5f4 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin3.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin3.q.out @@ -116,13 +116,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -143,13 +146,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin4.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin4.q.out index 8101595..4ed181a 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin4.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin4.q.out @@ -166,13 +166,16 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 4 Data size: 132 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 4 Data size: 132 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 132 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -195,13 +198,16 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 4 Data size: 132 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 4 Data size: 132 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 132 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out index 261802b..e9e41dc 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out @@ -229,18 +229,22 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: count(1) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -248,12 +252,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-5 Map Reduce Local Work @@ -286,13 +294,17 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin6.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin6.q.out index ec9fae1..467bce7 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin6.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin6.q.out @@ -114,39 +114,50 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - Lateral View Forward + Select Operator + SELECT * : (no compute) Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: array) - outputColumnNames: _col0, _col1 + Lateral View Forward Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - Lateral View Join Operator - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Select Operator - expressions: _col1 (type: array) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - UDTF Operator + Select Operator + expressions: _col0 (type: string), _col1 (type: array) + outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - function name: explode Lateral View Join Operator outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: array), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col1 (type: array) + outputColumnNames: _col0 + Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE + function name: explode + Lateral View Join Operator + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: array), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -167,39 +178,50 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - Lateral View Forward + Select Operator + SELECT * : (no compute) Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: array) - outputColumnNames: _col0, _col1 + Lateral View Forward Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - Lateral View Join Operator - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Select Operator - expressions: _col1 (type: array) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - UDTF Operator + Select Operator + expressions: _col0 (type: string), _col1 (type: array) + outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - function name: explode Lateral View Join Operator outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: array), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col1 (type: array) + outputColumnNames: _col0 + Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE + function name: explode + Lateral View Join Operator + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: array), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin7.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin7.q.out index 25ff20c..15ef5b3 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin7.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin7.q.out @@ -127,12 +127,15 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -153,12 +156,15 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -250,12 +256,15 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -276,12 +285,15 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out index c47755a..665c7cb 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out @@ -154,25 +154,28 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 val (type: string) - outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 val (type: string) + outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -189,25 +192,28 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 val (type: string) - outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 val (type: string) + outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/skewjoin_noskew.q.out b/ql/src/test/results/clientpositive/skewjoin_noskew.q.out index 24e07c2..e9965f9 100644 --- a/ql/src/test/results/clientpositive/skewjoin_noskew.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_noskew.q.out @@ -26,28 +26,28 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator @@ -55,16 +55,20 @@ STAGE PLANS: Inner Join 0 to 1 handleSkewJoin: true keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-6 Conditional Operator @@ -93,13 +97,17 @@ STAGE PLANS: keys: 0 reducesinkkey0 (type: string) 1 reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: key, value + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -108,14 +116,14 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 30 diff --git a/ql/src/test/results/clientpositive/skewjoinopt1.q.out b/ql/src/test/results/clientpositive/skewjoinopt1.q.out index f3aa0f7..09400c0 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt1.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt1.q.out @@ -106,23 +106,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce @@ -262,23 +268,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce @@ -400,12 +412,14 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -413,40 +427,50 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce @@ -478,12 +502,14 @@ STAGE PLANS: condition map: Inner Join 0 to 1 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -548,12 +574,14 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -561,40 +589,50 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce @@ -626,12 +664,14 @@ STAGE PLANS: condition map: Right Outer Join0 to 1 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/skewjoinopt10.q.out b/ql/src/test/results/clientpositive/skewjoinopt10.q.out index 7655cf3..732168b 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt10.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt10.q.out @@ -107,75 +107,97 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - Lateral View Forward + Select Operator + SELECT * : (no compute) Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: array) - outputColumnNames: _col0, _col1 + Lateral View Forward Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - Lateral View Join Operator - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Select Operator - expressions: _col1 (type: array) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - UDTF Operator + Select Operator + expressions: _col0 (type: string), _col1 (type: array) + outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - function name: explode Lateral View Join Operator outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: array), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col1 (type: array) + outputColumnNames: _col0 + Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE + function name: explode + Lateral View Join Operator + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: array), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - Lateral View Forward + Select Operator + SELECT * : (no compute) Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: array) - outputColumnNames: _col0, _col1 + Lateral View Forward Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - Lateral View Join Operator - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Select Operator - expressions: _col1 (type: array) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - UDTF Operator + Select Operator + expressions: _col0 (type: string), _col1 (type: array) + outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE - function name: explode Lateral View Join Operator outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: array), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col1 (type: array) + outputColumnNames: _col0 + Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 3 Data size: 41 Basic stats: COMPLETE Column stats: NONE + function name: explode + Lateral View Join Operator + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: array), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 82 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce diff --git a/ql/src/test/results/clientpositive/skewjoinopt11.q.out b/ql/src/test/results/clientpositive/skewjoinopt11.q.out index 121054b..b6b4aee 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt11.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt11.q.out @@ -122,21 +122,27 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -223,21 +229,27 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-8 Map Reduce diff --git a/ql/src/test/results/clientpositive/skewjoinopt12.q.out b/ql/src/test/results/clientpositive/skewjoinopt12.q.out index 7f5a932..c4a8c68 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt12.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt12.q.out @@ -106,23 +106,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce diff --git a/ql/src/test/results/clientpositive/skewjoinopt14.q.out b/ql/src/test/results/clientpositive/skewjoinopt14.q.out index 1e0d438..d30f862 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt14.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt14.q.out @@ -134,12 +134,15 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string) + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string) TableScan alias: c Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE @@ -155,12 +158,15 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string) + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string) Reduce Operator Tree: Join Operator condition map: diff --git a/ql/src/test/results/clientpositive/skewjoinopt15.q.out b/ql/src/test/results/clientpositive/skewjoinopt15.q.out index dbf68f1..9373dd1 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt15.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt15.q.out @@ -146,23 +146,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce @@ -302,23 +308,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce @@ -440,12 +452,14 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -453,40 +467,50 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) TableScan Union Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce @@ -518,12 +542,14 @@ STAGE PLANS: condition map: Inner Join 0 to 1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -588,12 +614,14 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -601,40 +629,50 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) TableScan Union Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + SELECT * : (no compute) + Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce @@ -666,12 +704,14 @@ STAGE PLANS: condition map: Right Outer Join0 to 1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/skewjoinopt16.q.out b/ql/src/test/results/clientpositive/skewjoinopt16.q.out index 937a65d..2d21bae 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt16.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt16.q.out @@ -106,23 +106,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce diff --git a/ql/src/test/results/clientpositive/skewjoinopt17.q.out b/ql/src/test/results/clientpositive/skewjoinopt17.q.out index 581e914..ddc606f 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt17.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt17.q.out @@ -112,23 +112,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce @@ -322,23 +328,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce diff --git a/ql/src/test/results/clientpositive/skewjoinopt19.q.out b/ql/src/test/results/clientpositive/skewjoinopt19.q.out index 91167db..7d8098e 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt19.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt19.q.out @@ -110,23 +110,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce diff --git a/ql/src/test/results/clientpositive/skewjoinopt2.q.out b/ql/src/test/results/clientpositive/skewjoinopt2.q.out index 132633f..05ff628 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt2.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt2.q.out @@ -114,23 +114,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce @@ -263,23 +269,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce @@ -399,12 +411,16 @@ STAGE PLANS: 1 key (type: string), val (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -412,33 +428,39 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -446,13 +468,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce @@ -485,12 +511,16 @@ STAGE PLANS: Inner Join 0 to 1 outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -557,12 +587,16 @@ STAGE PLANS: 1 key (type: string), val (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -570,33 +604,39 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -604,13 +644,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce @@ -643,12 +687,16 @@ STAGE PLANS: Left Outer Join0 to 1 outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/skewjoinopt20.q.out b/ql/src/test/results/clientpositive/skewjoinopt20.q.out index 15e96fd..25b4887 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt20.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt20.q.out @@ -110,23 +110,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce diff --git a/ql/src/test/results/clientpositive/skewjoinopt3.q.out b/ql/src/test/results/clientpositive/skewjoinopt3.q.out index fad53c3..9a14ecc 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt3.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt3.q.out @@ -110,23 +110,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce @@ -266,23 +272,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce diff --git a/ql/src/test/results/clientpositive/skewjoinopt4.q.out b/ql/src/test/results/clientpositive/skewjoinopt4.q.out index 1d2a5a4..6ade89b 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt4.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt4.q.out @@ -106,23 +106,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce @@ -260,23 +266,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce diff --git a/ql/src/test/results/clientpositive/skewjoinopt5.q.out b/ql/src/test/results/clientpositive/skewjoinopt5.q.out index f395da8..40e5dc5 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt5.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt5.q.out @@ -108,23 +108,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce diff --git a/ql/src/test/results/clientpositive/skewjoinopt6.q.out b/ql/src/test/results/clientpositive/skewjoinopt6.q.out index ac926f6..6a0917e 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt6.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt6.q.out @@ -110,23 +110,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce diff --git a/ql/src/test/results/clientpositive/skewjoinopt7.q.out b/ql/src/test/results/clientpositive/skewjoinopt7.q.out index 823ac41..855d2d4 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt7.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt7.q.out @@ -140,23 +140,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 4 Data size: 132 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 4 Data size: 132 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 132 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 4 Data size: 132 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 4 Data size: 132 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 132 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-5 Map Reduce diff --git a/ql/src/test/results/clientpositive/skewjoinopt8.q.out b/ql/src/test/results/clientpositive/skewjoinopt8.q.out index bcd4e3a..4dd9c16 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt8.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt8.q.out @@ -138,23 +138,29 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 4 Data size: 132 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 4 Data size: 132 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 132 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 4 Data size: 132 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + SELECT * : (no compute) Statistics: Num rows: 4 Data size: 132 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 132 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-5 Map Reduce diff --git a/ql/src/test/results/clientpositive/skewjoinopt9.q.out b/ql/src/test/results/clientpositive/skewjoinopt9.q.out index 6e76481..5d8b9e7 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt9.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt9.q.out @@ -208,18 +208,22 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: count(1) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -227,12 +231,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -265,13 +273,17 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_14.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_14.q.out index 28e62d2..884a73d 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_14.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_14.q.out @@ -70,24 +70,28 @@ STAGE PLANS: keys: 0 key (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -152,28 +156,34 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -270,16 +280,19 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -310,12 +323,15 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -390,24 +406,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -482,24 +502,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -602,24 +626,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -712,24 +740,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -823,15 +855,17 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -840,13 +874,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -907,24 +945,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -985,24 +1027,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1075,24 +1121,28 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1175,24 +1225,28 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_16.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_16.q.out index 6c78ee5..5b837dc 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_16.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_16.q.out @@ -62,24 +62,28 @@ STAGE PLANS: keys: 0 key (type: int) 1 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_17.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_17.q.out index 740f2df..04035b3 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_17.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_17.q.out @@ -210,24 +210,28 @@ STAGE PLANS: 4 key (type: int) 5 key (type: int) 6 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -317,24 +321,28 @@ STAGE PLANS: 4 key (type: int) 5 key (type: int) 6 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -424,24 +432,28 @@ STAGE PLANS: 5 key (type: int) 6 key (type: int) 7 key (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -631,12 +643,15 @@ STAGE PLANS: 3 key (type: int) 4 key (type: int) outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_18.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_18.q.out index 6106188..1efe83c 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_18.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_18.q.out @@ -58,7 +58,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -239,7 +239,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -356,7 +356,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_19.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_19.q.out index 95137cd..acc4871 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_19.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_19.q.out @@ -58,7 +58,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_21.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_21.q.out index 319fef3..bb6783d 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_21.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_21.q.out @@ -58,7 +58,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -128,14 +128,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: key (type: int) sort order: - - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: key (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) @@ -209,12 +209,12 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) + key expressions: key (type: int), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: key (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator @@ -289,14 +289,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: key (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + value expressions: key (type: int) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), KEY.reducesinkkey0 (type: string) @@ -370,14 +370,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: key (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: key (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) @@ -451,13 +451,13 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: key (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string) + value expressions: key (type: int), value (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string) diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_22.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_22.q.out index 8f1dbd6..cf0da80 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_22.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_22.q.out @@ -56,7 +56,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -200,7 +200,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/sort_merge_join_desc_1.q.out b/ql/src/test/results/clientpositive/sort_merge_join_desc_1.q.out index 63c4375..2635ee3 100644 --- a/ql/src/test/results/clientpositive/sort_merge_join_desc_1.q.out +++ b/ql/src/test/results/clientpositive/sort_merge_join_desc_1.q.out @@ -74,24 +74,28 @@ STAGE PLANS: keys: 0 key (type: string) 1 key (type: string) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/sort_merge_join_desc_2.q.out b/ql/src/test/results/clientpositive/sort_merge_join_desc_2.q.out index 398e711..52526cb 100644 --- a/ql/src/test/results/clientpositive/sort_merge_join_desc_2.q.out +++ b/ql/src/test/results/clientpositive/sort_merge_join_desc_2.q.out @@ -82,24 +82,28 @@ STAGE PLANS: keys: 0 key (type: string), value (type: string) 1 key (type: string), value (type: string) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/sort_merge_join_desc_3.q.out b/ql/src/test/results/clientpositive/sort_merge_join_desc_3.q.out index dc449fd..1acb9e5 100644 --- a/ql/src/test/results/clientpositive/sort_merge_join_desc_3.q.out +++ b/ql/src/test/results/clientpositive/sort_merge_join_desc_3.q.out @@ -82,24 +82,28 @@ STAGE PLANS: keys: 0 key (type: string), value (type: string) 1 key (type: string), value (type: string) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/sort_merge_join_desc_4.q.out b/ql/src/test/results/clientpositive/sort_merge_join_desc_4.q.out index 09b9622..337e699 100644 --- a/ql/src/test/results/clientpositive/sort_merge_join_desc_4.q.out +++ b/ql/src/test/results/clientpositive/sort_merge_join_desc_4.q.out @@ -101,15 +101,17 @@ STAGE PLANS: 0 key (type: string), value (type: string) 1 key (type: string), value (type: string) Statistics: Num rows: 45 Data size: 478 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 45 Data size: 478 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -118,13 +120,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/sort_merge_join_desc_5.q.out b/ql/src/test/results/clientpositive/sort_merge_join_desc_5.q.out index 91cd338..3373304 100644 --- a/ql/src/test/results/clientpositive/sort_merge_join_desc_5.q.out +++ b/ql/src/test/results/clientpositive/sort_merge_join_desc_5.q.out @@ -135,15 +135,16 @@ STAGE PLANS: 1 key (type: int) Position of Big Table: 0 BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -203,26 +204,29 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - GlobalTableId: 0 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 + NumFilesPerFileSink: 1 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/sort_merge_join_desc_6.q.out b/ql/src/test/results/clientpositive/sort_merge_join_desc_6.q.out index d5ae55e..a8a7f83 100644 --- a/ql/src/test/results/clientpositive/sort_merge_join_desc_6.q.out +++ b/ql/src/test/results/clientpositive/sort_merge_join_desc_6.q.out @@ -212,17 +212,19 @@ STAGE PLANS: Position of Big Table: 0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -285,27 +287,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/sort_merge_join_desc_7.q.out b/ql/src/test/results/clientpositive/sort_merge_join_desc_7.q.out index c4aa11b..22e0c44 100644 --- a/ql/src/test/results/clientpositive/sort_merge_join_desc_7.q.out +++ b/ql/src/test/results/clientpositive/sort_merge_join_desc_7.q.out @@ -285,17 +285,19 @@ STAGE PLANS: 1 key (type: int) Position of Big Table: 0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false Local Work: Map Reduce Local Work Path -> Alias: @@ -405,27 +407,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/sort_merge_join_desc_8.q.out b/ql/src/test/results/clientpositive/sort_merge_join_desc_8.q.out index d9c8cdc..7c1604f 100644 --- a/ql/src/test/results/clientpositive/sort_merge_join_desc_8.q.out +++ b/ql/src/test/results/clientpositive/sort_merge_join_desc_8.q.out @@ -127,24 +127,28 @@ STAGE PLANS: keys: 0 key (type: string) 1 key (type: string) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) + Select Operator + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Reduce Output Operator + sort order: + value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -218,15 +222,17 @@ STAGE PLANS: 0 key (type: string), value2 (type: string) 1 key (type: string), value2 (type: string) Statistics: Num rows: 45 Data size: 920 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 45 Data size: 920 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -235,13 +241,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/source.q.out b/ql/src/test/results/clientpositive/source.q.out index 82d9e23..d11fd39 100644 --- a/ql/src/test/results/clientpositive/source.q.out +++ b/ql/src/test/results/clientpositive/source.q.out @@ -17,7 +17,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink @@ -548,7 +548,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/stats0.q.out b/ql/src/test/results/clientpositive/stats0.q.out index 6e068dc..d165f37 100644 --- a/ql/src/test/results/clientpositive/stats0.q.out +++ b/ql/src/test/results/clientpositive/stats0.q.out @@ -46,7 +46,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -710,7 +710,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1366,7 +1366,7 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2188,7 +2188,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/stats1.q.out b/ql/src/test/results/clientpositive/stats1.q.out index ac34bbb..beb8d84 100644 --- a/ql/src/test/results/clientpositive/stats1.q.out +++ b/ql/src/test/results/clientpositive/stats1.q.out @@ -35,12 +35,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1:unionsrc-subquery1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -52,11 +54,11 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst1' (type: string), UDFToString(_col0) (type: string) - outputColumnNames: _col0, _col1 + expressions: 'tst1' (type: string), UDFToString($f0) (type: string) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -71,31 +73,39 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 26 Data size: 463 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false - Statistics: Num rows: 26 Data size: 463 Basic stats: COMPLETE Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmptable - TableScan - alias: s2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 26 Data size: 463 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 463 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.tmptable + TableScan + alias: null-subquery2:unionsrc-subquery2:s2 + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 26 Data size: 463 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: PARTIAL + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmptable Stage: Stage-0 Move Operator @@ -128,8 +138,8 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@tmptable -POSTHOOK: Lineage: tmptable.key EXPRESSION [(src1)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmptable.value EXPRESSION [(src1)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: tmptable.key EXPRESSION [(src1)null-subquery2:unionsrc-subquery2:s2.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: tmptable.value EXPRESSION [(src1)null-subquery2:unionsrc-subquery2:s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT * FROM tmptable x SORT BY x.key, x.value PREHOOK: type: QUERY PREHOOK: Input: default@tmptable diff --git a/ql/src/test/results/clientpositive/stats10.q.out b/ql/src/test/results/clientpositive/stats10.q.out index 7824cbd..ff31fd0 100644 --- a/ql/src/test/results/clientpositive/stats10.q.out +++ b/ql/src/test/results/clientpositive/stats10.q.out @@ -28,13 +28,13 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Map-reduce partition columns: UDFToInteger(_col0) (type: int) + Map-reduce partition columns: UDFToInteger(key) (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) + value expressions: key (type: string), value (type: string) Reduce Operator Tree: Select Operator expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string) diff --git a/ql/src/test/results/clientpositive/stats2.q.out b/ql/src/test/results/clientpositive/stats2.q.out index ac1d5cb..d4e21f3 100644 --- a/ql/src/test/results/clientpositive/stats2.q.out +++ b/ql/src/test/results/clientpositive/stats2.q.out @@ -25,7 +25,7 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: key, value, ds, hr Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/stats_empty_dyn_part.q.out b/ql/src/test/results/clientpositive/stats_empty_dyn_part.q.out index 982baab..554b648 100644 --- a/ql/src/test/results/clientpositive/stats_empty_dyn_part.q.out +++ b/ql/src/test/results/clientpositive/stats_empty_dyn_part.q.out @@ -40,7 +40,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'no_such_value' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/stats_only_null.q.out b/ql/src/test/results/clientpositive/stats_only_null.q.out index 55c5970..2718358 100644 --- a/ql/src/test/results/clientpositive/stats_only_null.q.out +++ b/ql/src/test/results/clientpositive/stats_only_null.q.out @@ -85,10 +85,10 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: double), b (type: int), c (type: string), d (type: smallint) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(_col0), count(_col1), count(_col2), count(_col3) + aggregations: count(), count(a), count(b), count(c), count(d) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE @@ -100,15 +100,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3, $f4 + Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint), $f4 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3, $f4 + Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -135,10 +139,10 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: double), b (type: int), c (type: string), d (type: smallint) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(_col0), count(_col1), count(_col2), count(_col3) + aggregations: count(), count(a), count(b), count(c), count(d) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE @@ -150,15 +154,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3, $f4 + Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint), $f4 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3, $f4 + Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/stats_ppr_all.q.out b/ql/src/test/results/clientpositive/stats_ppr_all.q.out index 5f6f5d4..12ff3a2 100644 --- a/ql/src/test/results/clientpositive/stats_ppr_all.q.out +++ b/ql/src/test/results/clientpositive/stats_ppr_all.q.out @@ -77,10 +77,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: order_amount (type: float) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -92,15 +92,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: double) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -128,10 +132,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: order_amount (type: float) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: PARTIAL Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: PARTIAL @@ -143,15 +147,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: double) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -176,10 +184,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: order_amount (type: float) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -191,15 +199,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: double) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -227,10 +239,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: order_amount (type: float) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -242,15 +254,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: double) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -278,7 +294,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '1' (type: string) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE ListSink diff --git a/ql/src/test/results/clientpositive/str_to_map.q.java1.7.out b/ql/src/test/results/clientpositive/str_to_map.q.java1.7.out index d985b2f..f3f18c9 100644 --- a/ql/src/test/results/clientpositive/str_to_map.q.java1.7.out +++ b/ql/src/test/results/clientpositive/str_to_map.q.java1.7.out @@ -30,7 +30,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: str_to_map('a=1,b=2,c=3',',','=')['a'] (type: string) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 500 Data size: 42500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 @@ -65,7 +65,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: str_to_map('a:1,b:2,c:3') (type: map) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 500 Data size: 377000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 @@ -100,7 +100,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: str_to_map('a:1,b:2,c:3',',',':') (type: map) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 500 Data size: 377000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 diff --git a/ql/src/test/results/clientpositive/subq.q.out b/ql/src/test/results/clientpositive/subq.q.out index 4b1e707..e810395 100644 --- a/ql/src/test/results/clientpositive/subq.q.out +++ b/ql/src/test/results/clientpositive/subq.q.out @@ -24,14 +24,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: unioninput:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/subq2.q.out b/ql/src/test/results/clientpositive/subq2.q.out index 8705af7..610abb2 100644 --- a/ql/src/test/results/clientpositive/subq2.q.out +++ b/ql/src/test/results/clientpositive/subq2.q.out @@ -17,18 +17,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: a:b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) >= 90.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -43,15 +43,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/subq_where_serialization.q.out b/ql/src/test/results/clientpositive/subq_where_serialization.q.out index c0b2a2d..bfb018f 100644 --- a/ql/src/test/results/clientpositive/subq_where_serialization.q.out +++ b/ql/src/test/results/clientpositive/subq_where_serialization.q.out @@ -15,17 +15,17 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: sq_1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -38,19 +38,14 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Conditional Operator @@ -66,8 +61,8 @@ STAGE PLANS: TableScan HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) Stage: Stage-3 Map Reduce @@ -80,23 +75,27 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -111,35 +110,39 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/subquery_alias.q.out b/ql/src/test/results/clientpositive/subquery_alias.q.out index a304512..0a60b60 100644 --- a/ql/src/test/results/clientpositive/subquery_alias.q.out +++ b/ql/src/test/results/clientpositive/subquery_alias.q.out @@ -24,14 +24,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: unioninput:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -105,11 +105,11 @@ STAGE PLANS: limit: -1 Processor Tree: TableScan - alias: s + alias: src2:src1:s Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/subquery_exists.q.out b/ql/src/test/results/clientpositive/subquery_exists.q.out index ace5efe..e09c8cb 100644 --- a/ql/src/test/results/clientpositive/subquery_exists.q.out +++ b/ql/src/test/results/clientpositive/subquery_exists.q.out @@ -36,53 +36,52 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((value > 'val_9') and key is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: ((value is not null and key is not null) and (value > 'val_9')) (type: boolean) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string), _col0 (type: string) + key expressions: value (type: string), key (type: string) sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col0 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: value (type: string), key (type: string) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE TableScan - alias: b + alias: sq_1:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((value > 'val_9') and key is not null) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: sq_corr_0, sq_corr_1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: sq_corr_0 (type: string), sq_corr_1 (type: string) + sort order: ++ + Map-reduce partition columns: sq_corr_0 (type: string), sq_corr_1 (type: string) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col1 (type: string), _col0 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + 0 value (type: string), key (type: string) + 1 sq_corr_0 (type: string), sq_corr_1 (type: string) + outputColumnNames: key, value Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/subquery_exists_having.q.out b/ql/src/test/results/clientpositive/subquery_exists_having.q.out index 14819c9..6272f57 100644 --- a/ql/src/test/results/clientpositive/subquery_exists_having.q.out +++ b/ql/src/test/results/clientpositive/subquery_exists_having.q.out @@ -37,11 +37,11 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -56,7 +56,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -70,47 +70,46 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) TableScan - alias: b + alias: sq_1:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((value > 'val_9') and key is not null) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: sq_corr_0 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: sq_corr_0 (type: string) + sort order: + + Map-reduce partition columns: sq_corr_0 (type: string) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 sq_corr_0 (type: string) + outputColumnNames: key, $f1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, $f1 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -184,11 +183,11 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -199,25 +198,20 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan - alias: b + alias: sq_1:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((value > 'val_9') and key is not null) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: sq_corr_0 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: sq_corr_0 (type: string) + sort order: + + Map-reduce partition columns: sq_corr_0 (type: string) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Demux Operator Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE @@ -225,7 +219,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 499 Data size: 5300 Basic stats: COMPLETE Column stats: NONE @@ -233,34 +227,42 @@ STAGE PLANS: condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 sq_corr_0 (type: string) + outputColumnNames: key, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator Statistics: Num rows: 499 Data size: 5300 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 sq_corr_0 (type: string) + outputColumnNames: key, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/subquery_in.q.out b/ql/src/test/results/clientpositive/subquery_in.q.out index f82c799..dba6d82 100644 --- a/ql/src/test/results/clientpositive/subquery_in.q.out +++ b/ql/src/test/results/clientpositive/subquery_in.q.out @@ -30,50 +30,49 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src + alias: sq_1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > '9') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -136,53 +135,52 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: ((value is not null and key is not null) and (key > '9')) (type: boolean) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE TableScan - alias: b + alias: sq_1:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: (((key > '9') and value is not null) and key is not null) (type: boolean) + Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 key (type: string), value (type: string) + 1 key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 46 Data size: 490 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 46 Data size: 490 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 46 Data size: 490 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -252,7 +250,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: part + alias: sq_1:a:part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_mfgr (type: string), p_size (type: int) @@ -262,38 +260,38 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) - outputColumnNames: _col2, _col5 + outputColumnNames: p_mfgr, p_size Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col2: string, _col5: int + output shape: p_mfgr: string, p_size: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col5 - partition by: _col2 + order by: p_size + partition by: p_mfgr raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col5 + alias: $win$_col_30 + arguments: p_size name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (rank_window_0 <= 2) (type: boolean) + predicate: ($win$_col_30 <= 2) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col5 (type: int) - outputColumnNames: _col0 + expressions: p_size (type: int) + outputColumnNames: p_size Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0) + aggregations: avg(p_size) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -316,22 +314,17 @@ STAGE PLANS: Group By Operator aggregations: avg(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col0 is not null (type: boolean) + predicate: $f0 is not null (type: boolean) Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce @@ -339,41 +332,48 @@ STAGE PLANS: TableScan alias: part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_name (type: string), p_size (type: int), UDFToDouble(p_size) (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col2 is not null (type: boolean) + Filter Operator + predicate: UDFToDouble(p_size) is not null (type: boolean) + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_name (type: string), p_size (type: int), UDFToDouble(p_size) (type: double) + outputColumnNames: p_name, p_size, EXPR$0 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: double) - sort order: + - Map-reduce partition columns: _col2 (type: double) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: int) + Filter Operator + predicate: UDFToDouble(EXPR$0) is not null (type: boolean) + Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: UDFToDouble(EXPR$0) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(EXPR$0) (type: double) + Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE + value expressions: p_name (type: string), p_size (type: int) TableScan Reduce Output Operator - key expressions: _col0 (type: double) + key expressions: $f0 (type: double) sort order: + - Map-reduce partition columns: _col0 (type: double) + Map-reduce partition columns: $f0 (type: double) Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col2 (type: double) - 1 _col0 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 UDFToDouble(EXPR$0) (type: double) + 1 $f0 (type: double) + outputColumnNames: p_name, p_size + Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_name (type: string), p_size (type: int) + outputColumnNames: p_name, p_size + Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -432,7 +432,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1:a:part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_mfgr (type: string), p_size (type: int) @@ -442,39 +442,39 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) - outputColumnNames: _col2, _col5 + outputColumnNames: p_mfgr, p_size Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col2: string, _col5: int + output shape: p_mfgr: string, p_size: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col5 - partition by: _col2 + order by: p_size + partition by: p_mfgr raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col5 + alias: $win$_col_32 + arguments: p_size name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((rank_window_0 <= 2) and _col2 is not null) (type: boolean) + predicate: (($win$_col_32 <= 2) and p_mfgr is not null) (type: boolean) Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col5 (type: int) - outputColumnNames: _col0, _col1 + expressions: p_mfgr (type: string), p_size (type: int) + outputColumnNames: p_mfgr, p_size Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col1) - keys: _col0 (type: string) + aggregations: min(p_size) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE @@ -500,26 +500,21 @@ STAGE PLANS: aggregations: min(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, $f1 Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col1 is not null (type: boolean) + predicate: $f1 is not null (type: boolean) Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int), _col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: $f1 (type: int), p_mfgr (type: string) + outputColumnNames: _o__c0, sq_corr_0 Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce @@ -528,36 +523,36 @@ STAGE PLANS: alias: b Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (p_size is not null and p_mfgr is not null) (type: boolean) + predicate: (p_mfgr is not null and p_size is not null) (type: boolean) Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: p_name, p_mfgr, p_size Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: int), _col1 (type: string) + key expressions: p_size (type: int), p_mfgr (type: string) sort order: ++ - Map-reduce partition columns: _col2 (type: int), _col1 (type: string) + Map-reduce partition columns: p_size (type: int), p_mfgr (type: string) Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + value expressions: p_name (type: string) TableScan Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) + key expressions: _o__c0 (type: int), sq_corr_0 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Map-reduce partition columns: _o__c0 (type: int), sq_corr_0 (type: string) Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col2 (type: int), _col1 (type: string) - 1 _col0 (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 p_size (type: int), p_mfgr (type: string) + 1 _o__c0 (type: int), sq_corr_0 (type: string) + outputColumnNames: p_name, p_mfgr, p_size Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: p_mfgr (type: string), p_name (type: string), p_size (type: int) + outputColumnNames: p_mfgr, p_name, p_size Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -627,42 +622,37 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: (((key > '9') and value is not null) and key is not null) (type: boolean) + Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: key, value + Statistics: Num rows: 21 Data size: 223 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce @@ -671,39 +661,43 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: ((value is not null and key is not null) and (key > '9')) (type: boolean) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 21 Data size: 223 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 key (type: string), value (type: string) + 1 key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 45 Data size: 478 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 45 Data size: 478 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 45 Data size: 478 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -789,49 +783,44 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: lineitem + alias: li Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((l_linenumber = 1) and l_orderkey is not null) and l_partkey is not null) (type: boolean) - Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE + predicate: ((l_orderkey is not null and l_partkey is not null) and (l_linenumber = 1)) (type: boolean) + Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: l_orderkey, l_partkey, l_suppkey + Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: l_orderkey (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) + Map-reduce partition columns: l_orderkey (type: int) + Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE + value expressions: l_partkey (type: int), l_suppkey (type: int) TableScan - alias: lineitem + alias: sq_1:lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((l_shipmode = 'AIR') and l_orderkey is not null) (type: boolean) Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int) - outputColumnNames: _col0 + outputColumnNames: l_orderkey Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: l_orderkey (type: int) + sort order: + + Map-reduce partition columns: l_orderkey (type: int) Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 + 0 l_orderkey (type: int) + 1 l_orderkey (type: int) + outputColumnNames: l_partkey, l_suppkey Statistics: Num rows: 27 Data size: 3298 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -845,29 +834,29 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col1 (type: int) + key expressions: l_partkey (type: int) sort order: + - Map-reduce partition columns: _col1 (type: int) + Map-reduce partition columns: l_partkey (type: int) Statistics: Num rows: 27 Data size: 3298 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int) + value expressions: l_suppkey (type: int) TableScan Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: l_partkey (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: l_partkey (type: int) Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 + 0 l_partkey (type: int) + 1 l_partkey (type: int) + outputColumnNames: l_partkey, l_suppkey Statistics: Num rows: 29 Data size: 3627 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int), _col2 (type: int) - outputColumnNames: _col0, _col1 + expressions: l_partkey (type: int), l_suppkey (type: int) + outputColumnNames: p_partkey, l_suppkey Statistics: Num rows: 29 Data size: 3627 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -881,17 +870,17 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: lineitem + alias: p:lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_partkey (type: int) - outputColumnNames: _col0 + outputColumnNames: l_partkey Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: l_partkey (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE @@ -904,7 +893,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: l_partkey Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/subquery_in_having.q.out b/ql/src/test/results/clientpositive/subquery_in_having.q.out index da1da06..26de8e7 100644 --- a/ql/src/test/results/clientpositive/subquery_in_having.q.out +++ b/ql/src/test/results/clientpositive/subquery_in_having.q.out @@ -73,11 +73,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -92,10 +92,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col1 is not null (type: boolean) + predicate: $f1 is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -109,50 +109,54 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col1 (type: bigint) + key expressions: $f1 (type: bigint) sort order: + - Map-reduce partition columns: _col1 (type: bigint) + Map-reduce partition columns: $f1 (type: bigint) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + value expressions: key (type: string) TableScan Reduce Output Operator - key expressions: _col0 (type: bigint) + key expressions: _o__c0 (type: bigint) sort order: + - Map-reduce partition columns: _col0 (type: bigint) + Map-reduce partition columns: _o__c0 (type: bigint) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col1 (type: bigint) - 1 _col0 (type: bigint) - outputColumnNames: _col0, _col1 + 0 $f1 (type: bigint) + 1 _o__c0 (type: bigint) + outputColumnNames: key, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: key, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: src + alias: sq_1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > '9') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -167,30 +171,25 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col1 + expressions: $f1 (type: bigint) + outputColumnNames: $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col1 is not null (type: boolean) + predicate: $f1 is not null (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 + expressions: $f1 (type: bigint) + outputColumnNames: _o__c0 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: bigint) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -289,11 +288,11 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -308,10 +307,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, $f2 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col2 is not null (type: boolean) + predicate: $f2 is not null (type: boolean) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -325,50 +324,54 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col2 (type: bigint), _col1 (type: string) + key expressions: $f2 (type: bigint), value (type: string) sort order: ++ - Map-reduce partition columns: _col2 (type: bigint), _col1 (type: string) + Map-reduce partition columns: $f2 (type: bigint), value (type: string) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + value expressions: key (type: string) TableScan Reduce Output Operator - key expressions: _col0 (type: bigint), _col1 (type: string) + key expressions: _o__c0 (type: bigint), sq_corr_0 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: bigint), _col1 (type: string) + Map-reduce partition columns: _o__c0 (type: bigint), sq_corr_0 (type: string) Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col2 (type: bigint), _col1 (type: string) - 1 _col0 (type: bigint), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 $f2 (type: bigint), value (type: string) + 1 _o__c0 (type: bigint), sq_corr_0 (type: string) + outputColumnNames: key, value, $f2 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), $f2 (type: bigint) + outputColumnNames: key, value, $f2 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key > '9') and value is not null) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string), _col1 (type: string) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE @@ -383,30 +386,25 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: bigint) - outputColumnNames: _col0, _col2 + expressions: $f0 (type: string), $f2 (type: bigint) + outputColumnNames: $f0, $f2 Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col2 is not null (type: boolean) + predicate: $f2 is not null (type: boolean) Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: bigint), _col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: $f2 (type: bigint), $f0 (type: string) + outputColumnNames: _o__c0, sq_corr_0 Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: bigint), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -456,11 +454,11 @@ STAGE PLANS: Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_mfgr (type: string), p_size (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, p_size Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col1) - keys: _col0 (type: string) + aggregations: avg(p_size) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE @@ -475,7 +473,7 @@ STAGE PLANS: aggregations: avg(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, $f1 Statistics: Num rows: 7 Data size: 740 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -489,50 +487,54 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: p_mfgr (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 7 Data size: 740 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double) + value expressions: $f1 (type: double) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: p_mfgr (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 2 Data size: 211 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 p_mfgr (type: string) + 1 p_mfgr (type: string) + outputColumnNames: p_mfgr, $f1 Statistics: Num rows: 7 Data size: 814 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: p_mfgr (type: string), $f1 (type: double) + outputColumnNames: p_mfgr, $f1 Statistics: Num rows: 7 Data size: 814 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 7 Data size: 814 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1:part_subq Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p_mfgr is not null (type: boolean) Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_mfgr (type: string), p_size (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, p_size Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), min(_col1) - keys: _col0 (type: string) + aggregations: max(p_size), min(p_size) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE @@ -547,26 +549,21 @@ STAGE PLANS: aggregations: max(VALUE._col0), min(VALUE._col1) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: p_mfgr, $f1, $f2 Statistics: Num rows: 7 Data size: 740 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col1 - _col2) < 20) (type: boolean) + predicate: (($f1 - $f2) < 20) (type: boolean) Statistics: Num rows: 2 Data size: 211 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: p_mfgr (type: string) + outputColumnNames: p_mfgr Statistics: Num rows: 2 Data size: 211 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 211 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -614,11 +611,11 @@ STAGE PLANS: Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_mfgr (type: string), p_size (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, p_size Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col1) - keys: _col0 (type: string) + aggregations: avg(p_size) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE @@ -629,18 +626,18 @@ STAGE PLANS: Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: struct) TableScan - alias: b + alias: sq_1:part_subq Statistics: Num rows: 30 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p_mfgr is not null (type: boolean) Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_mfgr (type: string), p_size (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, p_size Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), min(_col1) - keys: _col0 (type: string) + aggregations: max(p_size), min(p_size) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE @@ -657,7 +654,7 @@ STAGE PLANS: aggregations: avg(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, $f1 Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 20 Data size: 2114 Basic stats: COMPLETE Column stats: NONE @@ -665,29 +662,33 @@ STAGE PLANS: condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 p_mfgr (type: string) + 1 p_mfgr (type: string) + outputColumnNames: p_mfgr, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: p_mfgr (type: string), $f1 (type: double) + outputColumnNames: p_mfgr, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Group By Operator aggregations: max(VALUE._col0), min(VALUE._col1) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: p_mfgr, $f1, $f2 Statistics: Num rows: 15 Data size: 1586 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col1 - _col2) < 20) (type: boolean) + predicate: (($f1 - $f2) < 20) (type: boolean) Statistics: Num rows: 5 Data size: 528 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + expressions: p_mfgr (type: string) + outputColumnNames: p_mfgr Statistics: Num rows: 5 Data size: 528 Basic stats: COMPLETE Column stats: NONE Mux Operator Statistics: Num rows: 20 Data size: 2114 Basic stats: COMPLETE Column stats: NONE @@ -695,17 +696,21 @@ STAGE PLANS: condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 p_mfgr (type: string) + 1 p_mfgr (type: string) + outputColumnNames: p_mfgr, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: p_mfgr (type: string), $f1 (type: double) + outputColumnNames: p_mfgr, $f1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -786,46 +791,41 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: b + alias: sq_1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > '8') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE @@ -851,10 +851,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, $f2 Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col2 is not null (type: boolean) + predicate: $f2 is not null (type: boolean) Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -868,50 +868,54 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col2 (type: bigint) + key expressions: $f2 (type: bigint) sort order: + - Map-reduce partition columns: _col2 (type: bigint) + Map-reduce partition columns: $f2 (type: bigint) Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) + value expressions: key (type: string), value (type: string) TableScan Reduce Output Operator - key expressions: _col0 (type: bigint) + key expressions: _o__c0 (type: bigint) sort order: + - Map-reduce partition columns: _col0 (type: bigint) + Map-reduce partition columns: _o__c0 (type: bigint) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col2 (type: bigint) - 1 _col0 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + 0 $f2 (type: bigint) + 1 _o__c0 (type: bigint) + outputColumnNames: key, value, $f2 Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), $f2 (type: bigint) + outputColumnNames: key, value, $f2 Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-5 Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_2:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > '9') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -926,30 +930,25 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col1 + expressions: $f1 (type: bigint) + outputColumnNames: $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col1 is not null (type: boolean) + predicate: $f1 is not null (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 + expressions: $f1 (type: bigint) + outputColumnNames: _o__c0 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: bigint) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -1000,18 +999,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_2:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > '9') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -1026,30 +1025,25 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col1 + expressions: $f1 (type: bigint) + outputColumnNames: $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col1 is not null (type: boolean) + predicate: $f1 is not null (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 + expressions: $f1 (type: bigint) + outputColumnNames: _o__c0 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: bigint) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-7 Conditional Operator @@ -1065,8 +1059,8 @@ STAGE PLANS: TableScan HashTable Sink Operator keys: - 0 _col2 (type: bigint) - 1 _col0 (type: bigint) + 0 $f2 (type: bigint) + 1 _o__c0 (type: bigint) Stage: Stage-6 Map Reduce @@ -1076,17 +1070,21 @@ STAGE PLANS: condition map: Left Semi Join 0 to 1 keys: - 0 _col2 (type: bigint) - 1 _col0 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + 0 $f2 (type: bigint) + 1 _o__c0 (type: bigint) + outputColumnNames: key, value, $f2 Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), $f2 (type: bigint) + outputColumnNames: key, value, $f2 Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -1095,61 +1093,60 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col2 (type: bigint) + key expressions: $f2 (type: bigint) sort order: + - Map-reduce partition columns: _col2 (type: bigint) + Map-reduce partition columns: $f2 (type: bigint) Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) + value expressions: key (type: string), value (type: string) TableScan Reduce Output Operator - key expressions: _col0 (type: bigint) + key expressions: _o__c0 (type: bigint) sort order: + - Map-reduce partition columns: _col0 (type: bigint) + Map-reduce partition columns: _o__c0 (type: bigint) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col2 (type: bigint) - 1 _col0 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + 0 $f2 (type: bigint) + 1 _o__c0 (type: bigint) + outputColumnNames: key, value, $f2 Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), $f2 (type: bigint) + outputColumnNames: key, value, $f2 Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-10 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:b + sq_1:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:b + sq_1:src TableScan - alias: b + alias: sq_1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > '8') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + HashTable Sink Operator + keys: + 0 key (type: string) + 1 key (type: string) Stage: Stage-2 Map Reduce @@ -1162,19 +1159,19 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE @@ -1191,10 +1188,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, $f2 Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col2 is not null (type: boolean) + predicate: $f2 is not null (type: boolean) Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1246,11 +1243,11 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 1692 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_mfgr (type: string), p_name (type: string), p_size (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 8 Data size: 1692 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col2) - keys: _col0 (type: string), _col1 (type: string) + aggregations: avg($f2) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 8 Data size: 1692 Basic stats: COMPLETE Column stats: NONE @@ -1265,7 +1262,7 @@ STAGE PLANS: aggregations: avg(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 4 Data size: 846 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1288,8 +1285,8 @@ STAGE PLANS: TableScan HashTable Sink Operator keys: - 0 _col1 (type: string) - 1 _col0 (type: string) + 0 $f1 (type: string) + 1 first_value_window_0 (type: string) Stage: Stage-4 Map Reduce @@ -1299,17 +1296,21 @@ STAGE PLANS: condition map: Left Semi Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 $f1 (type: string) + 1 first_value_window_0 (type: string) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 8 Data size: 1861 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: string), $f2 (type: double) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 8 Data size: 1861 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 8 Data size: 1861 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -1318,39 +1319,43 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: $f1 (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: $f1 (type: string) Statistics: Num rows: 4 Data size: 846 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col2 (type: double) + value expressions: $f0 (type: string), $f2 (type: double) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: first_value_window_0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: first_value_window_0 (type: string) Statistics: Num rows: 8 Data size: 1692 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 $f1 (type: string) + 1 first_value_window_0 (type: string) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 8 Data size: 1861 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: string), $f2 (type: double) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 8 Data size: 1861 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 8 Data size: 1861 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: part_subq + alias: sq_1:part_subq Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_mfgr (type: string), p_size (type: int) @@ -1360,47 +1365,42 @@ STAGE PLANS: value expressions: p_name (type: string) Reduce Operator Tree: Select Operator - expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) - outputColumnNames: _col1, _col2, _col5 + expressions: VALUE.p_name (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) + outputColumnNames: p_name, p_mfgr, p_size Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col1: string, _col2: string, _col5: int + output shape: p_name: string, p_mfgr: string, p_size: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col5 - partition by: _col2 + order by: p_size + partition by: p_mfgr raw input shape: window functions: window function definition - alias: first_value_window_0 - arguments: _col1 + alias: $win$_col_35 + arguments: p_name name: first_value window function: GenericUDAFFirstValueEvaluator window frame: PRECEDING(MAX)~ Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: first_value_window_0 is not null (type: boolean) + predicate: $win$_col_35 is not null (type: boolean) Statistics: Num rows: 8 Data size: 1692 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: first_value_window_0 (type: string) - outputColumnNames: _col0 + expressions: $win$_col_35 (type: string) + outputColumnNames: first_value_window_0 Statistics: Num rows: 8 Data size: 1692 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 8 Data size: 1692 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/subquery_multiinsert.q.java1.7.out b/ql/src/test/results/clientpositive/subquery_multiinsert.q.java1.7.out index b668694..844e801 100644 --- a/ql/src/test/results/clientpositive/subquery_multiinsert.q.java1.7.out +++ b/ql/src/test/results/clientpositive/subquery_multiinsert.q.java1.7.out @@ -278,14 +278,18 @@ STAGE PLANS: 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_4 + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_4 Stage: Stage-0 Move Operator @@ -669,14 +673,18 @@ STAGE PLANS: 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_4 + File Output Operator + compressed: false + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_4 Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/subquery_notexists.q.out b/ql/src/test/results/clientpositive/subquery_notexists.q.out index 81b4137..e6268fb 100644 --- a/ql/src/test/results/clientpositive/subquery_notexists.q.out +++ b/ql/src/test/results/clientpositive/subquery_notexists.q.out @@ -31,43 +31,43 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string), _col0 (type: string) + key expressions: value (type: string), key (type: string) sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col0 (type: string) + Map-reduce partition columns: value (type: string), key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan - alias: b + alias: sq_1:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value > 'val_2') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: value (type: string), key (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: value (type: string), key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col1 (type: string), _col0 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col3 + 0 value (type: string), key (type: string) + 1 value (type: string), key (type: string) + outputColumnNames: key, value, key0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col3 is null (type: boolean) + predicate: key0 is null (type: boolean) Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -252,17 +252,17 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value > 'val_2') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -275,18 +275,14 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce @@ -296,35 +292,35 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: value (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + value expressions: key (type: string) TableScan Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: value (type: string) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col3 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key, value, value0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col3 is null (type: boolean) + predicate: value0 is null (type: boolean) Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/subquery_notexists_having.q.out b/ql/src/test/results/clientpositive/subquery_notexists_having.q.out index fd09901..bd4b4d9 100644 --- a/ql/src/test/results/clientpositive/subquery_notexists_having.q.out +++ b/ql/src/test/results/clientpositive/subquery_notexists_having.q.out @@ -34,10 +34,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -50,7 +50,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -64,40 +64,40 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col1 (type: string), _col0 (type: string) + key expressions: value (type: string), key (type: string) sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col0 (type: string) + Map-reduce partition columns: value (type: string), key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: b + alias: sq_1:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value > 'val_12') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: value (type: string), key (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: value (type: string), key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col1 (type: string), _col0 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col3 + 0 value (type: string), key (type: string) + 1 value (type: string), key (type: string) + outputColumnNames: key, value, key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col3 is null (type: boolean) + predicate: key0 is null (type: boolean) Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string) + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -186,10 +186,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -202,7 +202,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -216,32 +216,32 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: value (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + value expressions: key (type: string) TableScan Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: value (type: string) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col3 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key, value, value0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col3 is null (type: boolean) + predicate: value0 is null (type: boolean) Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string) + outputColumnNames: $f0, $f1 Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -255,17 +255,17 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value > 'val_12') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE @@ -278,18 +278,14 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/subquery_notin.q.out b/ql/src/test/results/clientpositive/subquery_notin.q.out index fd6d53b..7f13706 100644 --- a/ql/src/test/results/clientpositive/subquery_notin.q.out +++ b/ql/src/test/results/clientpositive/subquery_notin.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[13][tables = [src, ]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- non agg, non corr explain select * @@ -28,7 +28,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: sq_1_notin_nullcheck:sq_1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key > '2') and key is null) (type: boolean) @@ -48,19 +48,17 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + predicate: ($f0 = 0) (type: boolean) + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce @@ -70,16 +68,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) + value expressions: key (type: string), value (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -87,7 +85,7 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -101,41 +99,41 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src + alias: sq_1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > '2') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col3 is null (type: boolean) + predicate: key0 is null (type: boolean) Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -151,7 +149,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[13][tables = [src, ]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select * from src where src.key not in ( select key from src s1 where s1.key > '2') @@ -285,7 +283,7 @@ POSTHOOK: Input: default@src 199 val_199 199 val_199 2 val_2 -Warning: Shuffle Join JOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[17][tables = [b, ]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- non agg, corr explain select p_mfgr, b.p_name, p_size @@ -319,7 +317,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1_notin_nullcheck:sq_1:a:part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_mfgr (type: string), p_size (type: int) @@ -329,32 +327,32 @@ STAGE PLANS: value expressions: p_name (type: string) Reduce Operator Tree: Select Operator - expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) - outputColumnNames: _col1, _col2, _col5 + expressions: VALUE.p_name (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) + outputColumnNames: p_name, p_mfgr, p_size Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col1: string, _col2: string, _col5: int + output shape: p_name: string, p_mfgr: string, p_size: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col5 - partition by: _col2 + order by: p_size + partition by: p_mfgr raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col5 + alias: $win$_col_36 + arguments: p_size name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((rank_window_0 <= 2) and (_col1 is null or _col2 is null)) (type: boolean) + predicate: (($win$_col_36 <= 2) and (p_name is null or p_mfgr is null)) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE @@ -382,19 +380,17 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + predicate: ($f0 = 0) (type: boolean) + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce @@ -404,16 +400,16 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: p_name, p_mfgr, p_size Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -421,7 +417,7 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: p_name, p_mfgr, p_size Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -435,32 +431,32 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: p_name (type: string), p_mfgr (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: p_name (type: string), p_mfgr (type: string) Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int) + value expressions: p_size (type: int) TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: p_name (type: string), p_mfgr (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: p_name (type: string), p_mfgr (type: string) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col4 + 0 p_name (type: string), p_mfgr (type: string) + 1 p_name (type: string), p_mfgr (type: string) + outputColumnNames: p_name, p_mfgr, p_size, p_name0 Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col4 is null (type: boolean) + predicate: p_name0 is null (type: boolean) Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: p_mfgr (type: string), p_name (type: string), p_size (type: int) + outputColumnNames: p_mfgr, p_name, p_size Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -474,7 +470,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1:a:part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_mfgr (type: string), p_size (type: int) @@ -484,36 +480,36 @@ STAGE PLANS: value expressions: p_name (type: string) Reduce Operator Tree: Select Operator - expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) - outputColumnNames: _col1, _col2, _col5 + expressions: VALUE.p_name (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) + outputColumnNames: p_name, p_mfgr, p_size Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col1: string, _col2: string, _col5: int + output shape: p_name: string, p_mfgr: string, p_size: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col5 - partition by: _col2 + order by: p_size + partition by: p_mfgr raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col5 + alias: $win$_col_37 + arguments: p_size name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (rank_window_0 <= 2) (type: boolean) + predicate: ($win$_col_37 <= 2) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 + expressions: p_mfgr (type: string), p_name (type: string) + outputColumnNames: p_mfgr, p_name Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -528,7 +524,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[17][tables = [b, ]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select p_mfgr, b.p_name, p_size from part b where b.p_name not in @@ -567,7 +563,7 @@ Manufacturer#4 almond azure aquamarine papaya violet 12 Manufacturer#5 almond antique blue firebrick mint 31 Manufacturer#5 almond aquamarine dodger light gainsboro 46 Manufacturer#5 almond azure blanched chiffon midnight 23 -Warning: Shuffle Join JOIN[43][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[33][tables = [$hdt$_1, ]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: -- agg, non corr explain select p_name, p_size @@ -602,7 +598,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: part + alias: sq_1:a:part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_mfgr (type: string), p_size (type: int) @@ -612,38 +608,38 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) - outputColumnNames: _col2, _col5 + outputColumnNames: p_mfgr, p_size Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col2: string, _col5: int + output shape: p_mfgr: string, p_size: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col5 - partition by: _col2 + order by: p_size + partition by: p_mfgr raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col5 + alias: $win$_col_40 + arguments: p_size name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (rank_window_0 <= 2) (type: boolean) + predicate: ($win$_col_40 <= 2) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col5 (type: int) - outputColumnNames: _col0 + expressions: p_size (type: int) + outputColumnNames: p_size Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0) + aggregations: avg(p_size) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -666,7 +662,7 @@ STAGE PLANS: Group By Operator aggregations: avg(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -683,38 +679,36 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_name (type: string), p_size (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: p_name, p_size Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(_col1) (type: double) + key expressions: UDFToDouble(p_size) (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(_col1) (type: double) + Map-reduce partition columns: UDFToDouble(p_size) (type: double) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: int) + value expressions: p_name (type: string), p_size (type: int) TableScan Reduce Output Operator - key expressions: _col0 (type: double) + key expressions: $f0 (type: double) sort order: + - Map-reduce partition columns: _col0 (type: double) + Map-reduce partition columns: $f0 (type: double) Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: $f0 (type: double) Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 UDFToDouble(_col1) (type: double) - 1 _col0 (type: double) - outputColumnNames: _col0, _col1, _col2 + 0 UDFToDouble(p_size) (type: double) + 1 $f0 (type: double) + outputColumnNames: p_name, p_size, $f0 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col2 is null (type: boolean) - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -722,12 +716,12 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: int) + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + value expressions: p_name (type: string), p_size (type: int), $f0 (type: double) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -735,21 +729,28 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + outputColumnNames: p_name, p_size, $f0 + Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: $f0 is null (type: boolean) Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: p_name (type: string), p_size (type: int) + outputColumnNames: p_name, p_size + Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-5 Map Reduce Map Operator Tree: TableScan - alias: part + alias: sq_1_notin_nullcheck:sq_1:a:part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_mfgr (type: string), p_size (type: int) @@ -759,38 +760,38 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) - outputColumnNames: _col2, _col5 + outputColumnNames: p_mfgr, p_size Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col2: string, _col5: int + output shape: p_mfgr: string, p_size: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col5 - partition by: _col2 + order by: p_size + partition by: p_mfgr raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col5 + alias: $win$_col_41 + arguments: p_size name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (rank_window_0 <= 2) (type: boolean) + predicate: ($win$_col_41 <= 2) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col5 (type: int) - outputColumnNames: _col0 + expressions: p_size (type: int) + outputColumnNames: p_size Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0) + aggregations: avg(p_size) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -813,29 +814,25 @@ STAGE PLANS: Group By Operator aggregations: avg(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col0 is null (type: boolean) + predicate: $f0 is null (type: boolean) Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count() + mode: complete + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ($f0 = 0) (type: boolean) + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -843,7 +840,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[43][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[33][tables = [$hdt$_1, ]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: select p_name, p_size from part where part.p_size not in @@ -890,7 +887,7 @@ almond aquamarine sandy cyan gainsboro 18 almond aquamarine yellow dodger mint 7 almond azure aquamarine papaya violet 12 almond azure blanched chiffon midnight 23 -Warning: Shuffle Join JOIN[40][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[21][tables = [b, ]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- agg, corr explain select p_mfgr, p_name, p_size @@ -924,7 +921,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1_notin_nullcheck:sq_1:a:part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_mfgr (type: string), p_size (type: int) @@ -934,39 +931,39 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) - outputColumnNames: _col2, _col5 + outputColumnNames: p_mfgr, p_size Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col2: string, _col5: int + output shape: p_mfgr: string, p_size: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col5 - partition by: _col2 + order by: p_size + partition by: p_mfgr raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col5 + alias: $win$_col_44 + arguments: p_size name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (rank_window_0 <= 2) (type: boolean) + predicate: ($win$_col_44 <= 2) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col5 (type: int) - outputColumnNames: _col0, _col1 + expressions: p_mfgr (type: string), p_size (type: int) + outputColumnNames: p_mfgr, p_size Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col1) - keys: _col0 (type: string) + aggregations: min(p_size) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE @@ -992,10 +989,10 @@ STAGE PLANS: aggregations: min(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, $f1 Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col1 is null or _col0 is null) (type: boolean) + predicate: ($f1 is null or p_mfgr is null) (type: boolean) Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE @@ -1003,7 +1000,7 @@ STAGE PLANS: aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1017,25 +1014,23 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + predicate: ($f0 = 0) (type: boolean) + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce @@ -1045,16 +1040,16 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: p_name, p_mfgr, p_size Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -1062,7 +1057,7 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: p_name, p_mfgr, p_size Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1076,32 +1071,33 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col2 (type: int), _col1 (type: string) + key expressions: p_size (type: int), p_mfgr (type: string) sort order: ++ - Map-reduce partition columns: _col2 (type: int), _col1 (type: string) + Map-reduce partition columns: p_size (type: int), p_mfgr (type: string) Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + value expressions: p_name (type: string) TableScan Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) + key expressions: $f1 (type: int), p_mfgr (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Map-reduce partition columns: $f1 (type: int), p_mfgr (type: string) Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: int) Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col2 (type: int), _col1 (type: string) - 1 _col0 (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col4 + 0 p_size (type: int), p_mfgr (type: string) + 1 $f1 (type: int), p_mfgr (type: string) + outputColumnNames: p_name, p_mfgr, p_size, $f1 Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col4 is null (type: boolean) + predicate: $f1 is null (type: boolean) Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: p_mfgr (type: string), p_name (type: string), p_size (type: int) + outputColumnNames: p_mfgr, p_name, p_size Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1115,7 +1111,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1:a:part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_mfgr (type: string), p_size (type: int) @@ -1125,39 +1121,39 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) - outputColumnNames: _col2, _col5 + outputColumnNames: p_mfgr, p_size Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col2: string, _col5: int + output shape: p_mfgr: string, p_size: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col5 - partition by: _col2 + order by: p_size + partition by: p_mfgr raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col5 + alias: $win$_col_45 + arguments: p_size name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (rank_window_0 <= 2) (type: boolean) + predicate: ($win$_col_45 <= 2) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col5 (type: int) - outputColumnNames: _col0, _col1 + expressions: p_mfgr (type: string), p_size (type: int) + outputColumnNames: p_mfgr, p_size Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col1) - keys: _col0 (type: string) + aggregations: min(p_size) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE @@ -1183,18 +1179,14 @@ STAGE PLANS: aggregations: min(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, $f1 Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -1202,7 +1194,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[40][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[21][tables = [b, ]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select p_mfgr, p_name, p_size from part b where b.p_size not in (select min(p_size) @@ -1243,7 +1235,7 @@ Manufacturer#5 almond antique medium spring khaki 6 Manufacturer#5 almond azure blanched chiffon midnight 23 Manufacturer#5 almond antique blue firebrick mint 31 Manufacturer#5 almond aquamarine dodger light gainsboro 46 -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[14][tables = [li, ]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- non agg, non corr, Group By in Parent Query select li.l_partkey, count(*) from lineitem li @@ -1278,7 +1270,7 @@ POSTHOOK: Input: default@lineitem 139636 1 175839 1 182052 1 -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[13][tables = [src, ]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- alternate not in syntax select * from src @@ -1442,7 +1434,7 @@ POSTHOOK: Input: default@src POSTHOOK: Input: default@t1_v POSTHOOK: Output: database:default POSTHOOK: Output: default@T2_v -Warning: Shuffle Join JOIN[25][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[14][tables = [t1_v:src, ]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select * from T1_v where T1_v.key not in (select T2_v.key from T2_v) @@ -1462,7 +1454,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: sq_1_notin_nullcheck:sq_1:t2_v:t1_v:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key < '11') and CASE WHEN ((key > '104')) THEN (null) ELSE (key) END is null) (type: boolean) @@ -1482,41 +1474,39 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + predicate: ($f0 = 0) (type: boolean) + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: src + alias: t1_v:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key < '11') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + value expressions: key (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -1524,7 +1514,7 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1538,48 +1528,53 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE TableScan - alias: src + alias: sq_1:t2_v:t1_v:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key < '11') and (CASE WHEN ((key > '104')) THEN (null) ELSE (key) END < '11')) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: CASE WHEN ((key > '104')) THEN (null) ELSE (key) END (type: string) - outputColumnNames: _col0 + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: CASE WHEN ((key > '104')) THEN (null) ELSE (key) END (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: CASE WHEN ((key > '104')) THEN (null) ELSE (key) END (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: string) Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 + 0 key (type: string) + 1 CASE WHEN ((key > '104')) THEN (null) ELSE (key) END (type: string) + outputColumnNames: key, key0 Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col2 is null (type: boolean) - Statistics: Num rows: 100 Data size: 1066 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Select Operator + expressions: key (type: string), CASE WHEN ((key0 > '104')) THEN (null) ELSE (key0) END (type: string) + outputColumnNames: key, key0 + Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key0 is null (type: boolean) Statistics: Num rows: 100 Data size: 1066 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 100 Data size: 1066 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 1066 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1587,7 +1582,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[25][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[14][tables = [t1_v:src, ]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select * from T1_v where T1_v.key not in (select T2_v.key from T2_v) PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out b/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out index 775f477..1750932 100644 --- a/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out +++ b/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join JOIN[26][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[16][tables = [, ]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: -- non agg, non corr -- JAVA_VERSION_SPECIFIC_OUTPUT @@ -39,11 +39,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -58,7 +58,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -74,11 +74,11 @@ STAGE PLANS: Reduce Output Operator sort order: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: bigint) + value expressions: key (type: string), $f1 (type: bigint) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -86,7 +86,7 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -100,41 +100,41 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) TableScan - alias: src + alias: sq_1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > '12') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, $f1, key0 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col3 is null (type: boolean) + predicate: key0 is null (type: boolean) Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: key (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -148,7 +148,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: sq_1_notin_nullcheck:sq_1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key > '12') and key is null) (type: boolean) @@ -168,19 +168,17 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + predicate: ($f0 = 0) (type: boolean) + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -188,7 +186,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[36][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[20][tables = [, ]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: -- non agg, corr explain select b.p_mfgr, min(p_retailprice) @@ -229,11 +227,11 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, p_retailprice Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col1) - keys: _col0 (type: string) + aggregations: min(p_retailprice) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE @@ -248,7 +246,7 @@ STAGE PLANS: aggregations: min(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, $f1 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -264,11 +262,11 @@ STAGE PLANS: Reduce Output Operator sort order: Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: double) + value expressions: p_mfgr (type: string), $f1 (type: double) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -276,7 +274,7 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, $f1 Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -290,31 +288,31 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double) + key expressions: p_mfgr (type: string), $f1 (type: double) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: double) + Map-reduce partition columns: p_mfgr (type: string), $f1 (type: double) Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double) + key expressions: p_mfgr (type: string), $f1 (type: double) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: double) + Map-reduce partition columns: p_mfgr (type: string), $f1 (type: double) Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string), _col1 (type: double) - 1 _col0 (type: string), _col1 (type: double) - outputColumnNames: _col0, _col1, _col3 + 0 p_mfgr (type: string), $f1 (type: double) + 1 p_mfgr (type: string), $f1 (type: double) + outputColumnNames: p_mfgr, $f1, p_mfgr0 Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col3 is null (type: boolean) + predicate: p_mfgr0 is null (type: boolean) Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: double) - outputColumnNames: _col0, _col1 + expressions: p_mfgr (type: string), $f1 (type: double) + outputColumnNames: $f0, $f1 Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -328,15 +326,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1_notin_nullcheck:sq_1:a:part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, p_retailprice Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col1), max(_col1) - keys: _col0 (type: string) + aggregations: min(p_retailprice), max(p_retailprice) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE @@ -351,10 +349,10 @@ STAGE PLANS: aggregations: min(VALUE._col0), max(VALUE._col1) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: p_mfgr, $f1, $f2 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col0 is null or _col1 is null) and ((_col2 - _col1) > 600.0)) (type: boolean) + predicate: ((p_mfgr is null or $f1 is null) and (($f2 - $f1) > 600.0)) (type: boolean) Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE @@ -362,7 +360,7 @@ STAGE PLANS: aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -376,39 +374,37 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + predicate: ($f0 = 0) (type: boolean) + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-6 Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1:a:part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, p_retailprice Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col1), max(_col1) - keys: _col0 (type: string) + aggregations: min(p_retailprice), max(p_retailprice) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE @@ -423,21 +419,17 @@ STAGE PLANS: aggregations: min(VALUE._col0), max(VALUE._col1) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: p_mfgr, $f1, $f2 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col2 - _col1) > 600.0) (type: boolean) + predicate: (($f2 - $f1) > 600.0) (type: boolean) Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -445,7 +437,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[36][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[20][tables = [, ]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: select b.p_mfgr, min(p_retailprice) from part b group by b.p_mfgr @@ -470,7 +462,7 @@ POSTHOOK: Input: default@part #### A masked pattern was here #### Manufacturer#1 1173.15 Manufacturer#2 1690.68 -Warning: Shuffle Join JOIN[39][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product +Warning: Shuffle Join JOIN[29][tables = [$hdt$_1, ]] in Stage 'Stage-3:MAPRED' is a cross product PREHOOK: query: -- agg, non corr explain select b.p_mfgr, min(p_retailprice) @@ -513,11 +505,11 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, p_retailprice Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col1) - keys: _col0 (type: string) + aggregations: min(p_retailprice) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE @@ -532,7 +524,7 @@ STAGE PLANS: aggregations: min(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, $f1 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -546,35 +538,32 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: p_mfgr (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double) + value expressions: $f1 (type: double) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: p_mfgr (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 p_mfgr (type: string) + 1 p_mfgr (type: string) + outputColumnNames: p_mfgr, $f1, p_mfgr0 Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col2 is null (type: boolean) - Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -582,12 +571,12 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: double) + Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + value expressions: p_mfgr (type: string), $f1 (type: double), p_mfgr0 (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -595,29 +584,36 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 951 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 7 Data size: 951 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: p_mfgr, $f1, p_mfgr0 + Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: p_mfgr0 is null (type: boolean) + Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_mfgr (type: string), $f1 (type: double) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1:a Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, p_retailprice Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), min(_col1) - keys: _col0 (type: string) + aggregations: max(p_retailprice), min(p_retailprice) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE @@ -632,38 +628,34 @@ STAGE PLANS: aggregations: max(VALUE._col0), min(VALUE._col1) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: p_mfgr, $f1, $f2 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col1 - _col2) > 600.0) (type: boolean) + predicate: (($f1 - $f2) > 600.0) (type: boolean) Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-5 Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1_notin_nullcheck:sq_1:a Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p_mfgr is null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: null (type: string), p_retailprice (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, p_retailprice Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), min(_col1) - keys: _col0 (type: string) + aggregations: max(p_retailprice), min(p_retailprice) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE @@ -678,14 +670,14 @@ STAGE PLANS: aggregations: max(VALUE._col0), min(VALUE._col1) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: p_mfgr, $f1, $f2 Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: double), _col2 (type: double) - outputColumnNames: _col1, _col2 + expressions: $f1 (type: double), $f2 (type: double) + outputColumnNames: $f1, $f2 Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col1 - _col2) > 600.0) (type: boolean) + predicate: (($f1 - $f2) > 600.0) (type: boolean) Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE @@ -693,7 +685,7 @@ STAGE PLANS: aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -707,25 +699,23 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + predicate: ($f0 = 0) (type: boolean) + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -733,7 +723,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[39][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product +Warning: Shuffle Join JOIN[29][tables = [$hdt$_1, ]] in Stage 'Stage-3:MAPRED' is a cross product PREHOOK: query: select b.p_mfgr, min(p_retailprice) from part b group by b.p_mfgr diff --git a/ql/src/test/results/clientpositive/subquery_unqual_corr_expr.q.out b/ql/src/test/results/clientpositive/subquery_unqual_corr_expr.q.out index 0234c17..e80f2b9 100644 --- a/ql/src/test/results/clientpositive/subquery_unqual_corr_expr.q.out +++ b/ql/src/test/results/clientpositive/subquery_unqual_corr_expr.q.out @@ -54,13 +54,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out b/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out index 76d7503..6ac8c46 100644 --- a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out +++ b/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out @@ -52,53 +52,52 @@ STAGE PLANS: alias: src11 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((key1 > '9') and value1 is not null) (type: boolean) + predicate: ((value1 is not null and key1 is not null) and (key1 > '9')) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key1 (type: string), value1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key1, value1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key1 (type: string), value1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: key1 (type: string), value1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE TableScan - alias: src + alias: sq_1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: (((key > '9') and value is not null) and key is not null) (type: boolean) + Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 key1 (type: string), value1 (type: string) + 1 key (type: string), value (type: string) + outputColumnNames: key1, value1 + Statistics: Num rows: 46 Data size: 490 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key1 (type: string), value1 (type: string) + outputColumnNames: key1, value1 + Statistics: Num rows: 46 Data size: 490 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 46 Data size: 490 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -122,53 +121,52 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: ((value is not null and key is not null) and (key > '9')) (type: boolean) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE TableScan - alias: a + alias: sq_1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: (((key > '9') and value is not null) and key is not null) (type: boolean) + Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 key (type: string), value (type: string) + 1 key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 46 Data size: 490 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 46 Data size: 490 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 46 Data size: 490 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -205,7 +203,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: part2 + alias: sq_1:a:part2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: p2_mfgr (type: string), p2_size (type: int) @@ -215,39 +213,39 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) - outputColumnNames: _col2, _col5 + outputColumnNames: p2_mfgr, p2_size Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col2: string, _col5: int + output shape: p2_mfgr: string, p2_size: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col5 - partition by: _col2 + order by: p2_size + partition by: p2_mfgr raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col5 + alias: $win$_col_48 + arguments: p2_size name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((rank_window_0 <= 2) and _col2 is not null) (type: boolean) + predicate: (($win$_col_48 <= 2) and p2_mfgr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col2 (type: string), _col5 (type: int) - outputColumnNames: _col0, _col1 + expressions: p2_mfgr (type: string), p2_size (type: int) + outputColumnNames: p2_mfgr, p2_size Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: min(_col1) - keys: _col0 (type: string) + aggregations: min(p2_size) + keys: p2_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -273,26 +271,21 @@ STAGE PLANS: aggregations: min(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: p2_mfgr, $f1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: _col1 is not null (type: boolean) + predicate: $f1 is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col1 (type: int), _col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: $f1 (type: int), p2_mfgr (type: string) + outputColumnNames: _o__c0, sq_corr_0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - keys: _col0 (type: int), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce @@ -301,36 +294,36 @@ STAGE PLANS: alias: b Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (p_size is not null and p_mfgr is not null) (type: boolean) + predicate: (p_mfgr is not null and p_size is not null) (type: boolean) Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: p_name, p_mfgr, p_size Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: int), _col1 (type: string) + key expressions: p_size (type: int), p_mfgr (type: string) sort order: ++ - Map-reduce partition columns: _col2 (type: int), _col1 (type: string) + Map-reduce partition columns: p_size (type: int), p_mfgr (type: string) Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + value expressions: p_name (type: string) TableScan Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) + key expressions: _o__c0 (type: int), sq_corr_0 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Map-reduce partition columns: _o__c0 (type: int), sq_corr_0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col2 (type: int), _col1 (type: string) - 1 _col0 (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 p_size (type: int), p_mfgr (type: string) + 1 _o__c0 (type: int), sq_corr_0 (type: string) + outputColumnNames: p_name, p_mfgr, p_size Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: p_mfgr (type: string), p_name (type: string), p_size (type: int) + outputColumnNames: p_mfgr, p_name, p_size Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -373,7 +366,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1:a:part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_mfgr (type: string), p_size (type: int) @@ -383,39 +376,39 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) - outputColumnNames: _col2, _col5 + outputColumnNames: p_mfgr, p_size Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col2: string, _col5: int + output shape: p_mfgr: string, p_size: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col5 - partition by: _col2 + order by: p_size + partition by: p_mfgr raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col5 + alias: $win$_col_49 + arguments: p_size name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((rank_window_0 <= 2) and _col2 is not null) (type: boolean) + predicate: (($win$_col_49 <= 2) and p_mfgr is not null) (type: boolean) Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col5 (type: int) - outputColumnNames: _col0, _col1 + expressions: p_mfgr (type: string), p_size (type: int) + outputColumnNames: p_mfgr, p_size Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col1) - keys: _col0 (type: string) + aggregations: min(p_size) + keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE @@ -441,26 +434,21 @@ STAGE PLANS: aggregations: min(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: p_mfgr, $f1 Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col1 is not null (type: boolean) + predicate: $f1 is not null (type: boolean) Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int), _col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: $f1 (type: int), p_mfgr (type: string) + outputColumnNames: _o__c0, sq_corr_0 Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce @@ -469,36 +457,36 @@ STAGE PLANS: alias: b Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (p_size is not null and p_mfgr is not null) (type: boolean) + predicate: (p_mfgr is not null and p_size is not null) (type: boolean) Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: p_name, p_mfgr, p_size Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: int), _col1 (type: string) + key expressions: p_size (type: int), p_mfgr (type: string) sort order: ++ - Map-reduce partition columns: _col2 (type: int), _col1 (type: string) + Map-reduce partition columns: p_size (type: int), p_mfgr (type: string) Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + value expressions: p_name (type: string) TableScan Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) + key expressions: _o__c0 (type: int), sq_corr_0 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Map-reduce partition columns: _o__c0 (type: int), sq_corr_0 (type: string) Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col2 (type: int), _col1 (type: string) - 1 _col0 (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 p_size (type: int), p_mfgr (type: string) + 1 _o__c0 (type: int), sq_corr_0 (type: string) + outputColumnNames: p_name, p_mfgr, p_size Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: p_mfgr (type: string), p_name (type: string), p_size (type: int) + outputColumnNames: p_mfgr, p_name, p_size Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -544,42 +532,37 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: (((key > '9') and value is not null) and key is not null) (type: boolean) + Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: key, value + Statistics: Num rows: 21 Data size: 223 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce @@ -588,39 +571,43 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: ((value is not null and key is not null) and (key > '9')) (type: boolean) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 21 Data size: 223 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 key (type: string), value (type: string) + 1 key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 45 Data size: 478 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 45 Data size: 478 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 45 Data size: 478 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -660,11 +647,11 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -679,10 +666,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, $f2 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col2 is not null (type: boolean) + predicate: $f2 is not null (type: boolean) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -696,50 +683,54 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col2 (type: bigint), _col1 (type: string) + key expressions: $f2 (type: bigint), value (type: string) sort order: ++ - Map-reduce partition columns: _col2 (type: bigint), _col1 (type: string) + Map-reduce partition columns: $f2 (type: bigint), value (type: string) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + value expressions: key (type: string) TableScan Reduce Output Operator - key expressions: _col0 (type: bigint), _col1 (type: string) + key expressions: _o__c0 (type: bigint), sq_corr_0 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: bigint), _col1 (type: string) + Map-reduce partition columns: _o__c0 (type: bigint), sq_corr_0 (type: string) Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col2 (type: bigint), _col1 (type: string) - 1 _col0 (type: bigint), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 + 0 $f2 (type: bigint), value (type: string) + 1 _o__c0 (type: bigint), sq_corr_0 (type: string) + outputColumnNames: key, value, $f2 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), $f2 (type: bigint) + outputColumnNames: key, value, $f2 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key > '9') and value is not null) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string), _col1 (type: string) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE @@ -754,30 +745,25 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: bigint) - outputColumnNames: _col0, _col2 + expressions: $f0 (type: string), $f2 (type: bigint) + outputColumnNames: $f0, $f2 Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col2 is not null (type: boolean) + predicate: $f2 is not null (type: boolean) Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: bigint), _col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: $f2 (type: bigint), $f0 (type: string) + outputColumnNames: _o__c0, sq_corr_0 Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: bigint), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -785,7 +771,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[17][tables = [b, ]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- non agg, corr explain select p_mfgr, b.p_name, p_size @@ -819,7 +805,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1_notin_nullcheck:sq_1:a:part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_mfgr (type: string), p_size (type: int) @@ -829,32 +815,32 @@ STAGE PLANS: value expressions: p_name (type: string) Reduce Operator Tree: Select Operator - expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) - outputColumnNames: _col1, _col2, _col5 + expressions: VALUE.p_name (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) + outputColumnNames: p_name, p_mfgr, p_size Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col1: string, _col2: string, _col5: int + output shape: p_name: string, p_mfgr: string, p_size: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col5 - partition by: _col2 + order by: p_size + partition by: p_mfgr raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col5 + alias: $win$_col_50 + arguments: p_size name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((rank_window_0 <= 2) and (_col1 is null or _col2 is null)) (type: boolean) + predicate: (($win$_col_50 <= 2) and (p_name is null or p_mfgr is null)) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE @@ -882,19 +868,17 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + predicate: ($f0 = 0) (type: boolean) + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce @@ -904,16 +888,16 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: p_name, p_mfgr, p_size Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -921,7 +905,7 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: p_name, p_mfgr, p_size Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -935,32 +919,32 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: p_name (type: string), p_mfgr (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: p_name (type: string), p_mfgr (type: string) Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int) + value expressions: p_size (type: int) TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: p_name (type: string), p_mfgr (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: p_name (type: string), p_mfgr (type: string) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col4 + 0 p_name (type: string), p_mfgr (type: string) + 1 p_name (type: string), p_mfgr (type: string) + outputColumnNames: p_name, p_mfgr, p_size, p_name0 Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col4 is null (type: boolean) + predicate: p_name0 is null (type: boolean) Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: p_mfgr (type: string), p_name (type: string), p_size (type: int) + outputColumnNames: p_mfgr, p_name, p_size Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -974,7 +958,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1:a:part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_mfgr (type: string), p_size (type: int) @@ -984,36 +968,36 @@ STAGE PLANS: value expressions: p_name (type: string) Reduce Operator Tree: Select Operator - expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) - outputColumnNames: _col1, _col2, _col5 + expressions: VALUE.p_name (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) + outputColumnNames: p_name, p_mfgr, p_size Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col1: string, _col2: string, _col5: int + output shape: p_name: string, p_mfgr: string, p_size: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col5 - partition by: _col2 + order by: p_size + partition by: p_mfgr raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col5 + alias: $win$_col_51 + arguments: p_size name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (rank_window_0 <= 2) (type: boolean) + predicate: ($win$_col_51 <= 2) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 + expressions: p_mfgr (type: string), p_name (type: string) + outputColumnNames: p_mfgr, p_name Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/subquery_views.q.out b/ql/src/test/results/clientpositive/subquery_views.q.out index c59d86e..e815778 100644 --- a/ql/src/test/results/clientpositive/subquery_views.q.out +++ b/ql/src/test/results/clientpositive/subquery_views.q.out @@ -69,8 +69,8 @@ POSTHOOK: type: CREATEVIEW POSTHOOK: Input: default@src POSTHOOK: Output: database:default POSTHOOK: Output: default@cv2 -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -Warning: Shuffle Join JOIN[52][tables = [$hdt$_1, $hdt$_2]] in Stage 'Stage-6:MAPRED' is a cross product +Warning: Shuffle Join JOIN[14][tables = [cv2:b, ]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[42][tables = [sq_1:c:b, ]] in Stage 'Stage-6:MAPRED' is a cross product PREHOOK: query: explain select * from cv2 where cv2.key in (select key from cv2 c where c.key < '11') @@ -94,7 +94,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: b + alias: cv2:sq_1_notin_nullcheck:sq_1:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((value > 'val_11') and (key is null or value is null or key is null)) (type: boolean) @@ -114,41 +114,36 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + predicate: ($f0 = 0) (type: boolean) + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: b + alias: cv2:b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < '11') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: string), value (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -156,8 +151,8 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -170,41 +165,41 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col0 (type: string) - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col0 (type: string) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE TableScan - alias: b + alias: cv2:sq_1:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((value > 'val_11') and (key < '11')) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: (value > 'val_11') (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string), key (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string), _col0 (type: string) - 1 _col0 (type: string), _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string), value (type: string) + 1 key (type: string), value (type: string) + outputColumnNames: key, value, key0 + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col3 is null (type: boolean) - Statistics: Num rows: 100 Data size: 1066 Basic stats: COMPLETE Column stats: NONE + predicate: ((key0 is null and key is not null) and (key < '11')) (type: boolean) + Statistics: Num rows: 50 Data size: 531 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 1066 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 50 Data size: 531 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -217,39 +212,43 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 100 Data size: 1066 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 50 Data size: 531 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 100 Data size: 1066 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 50 Data size: 531 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 110 Data size: 1172 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 110 Data size: 1172 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-8 Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1:c:sq_1_notin_nullcheck:sq_1:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((value > 'val_11') and (key is null or value is null or key is null)) (type: boolean) @@ -269,41 +268,36 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + predicate: ($f0 = 0) (type: boolean) + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-6 Map Reduce Map Operator Tree: TableScan - alias: b + alias: sq_1:c:b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < '11') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: string), value (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -311,8 +305,8 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -325,52 +319,47 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col0 (type: string) - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col0 (type: string) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE TableScan - alias: b + alias: sq_1:c:sq_1:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((value > 'val_11') and (key < '11')) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: (value > 'val_11') (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string), key (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string), _col0 (type: string) - 1 _col0 (type: string), _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE + 0 key (type: string), value (type: string) + 1 key (type: string), value (type: string) + outputColumnNames: key, key0 + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col3 is null (type: boolean) - Statistics: Num rows: 100 Data size: 1066 Basic stats: COMPLETE Column stats: NONE + predicate: ((key0 is null and (key < '11')) and key is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 531 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 100 Data size: 1066 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 100 Data size: 1066 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 50 Data size: 531 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -378,8 +367,8 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -Warning: Shuffle Join JOIN[52][tables = [$hdt$_1, $hdt$_2]] in Stage 'Stage-6:MAPRED' is a cross product +Warning: Shuffle Join JOIN[14][tables = [cv2:b, ]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[42][tables = [sq_1:c:b, ]] in Stage 'Stage-6:MAPRED' is a cross product PREHOOK: query: select * from cv2 where cv2.key in (select key from cv2 c where c.key < '11') PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/symlink_text_input_format.q.out b/ql/src/test/results/clientpositive/symlink_text_input_format.q.out index 6c2e2e6..998839c 100644 --- a/ql/src/test/results/clientpositive/symlink_text_input_format.q.out +++ b/ql/src/test/results/clientpositive/symlink_text_input_format.q.out @@ -45,16 +45,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) + key expressions: key (type: string), value (type: string) sort order: ++ Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -111,16 +111,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: value (type: string) sort order: + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -176,9 +176,11 @@ STAGE PLANS: alias: symlink_text_input_format Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -190,15 +192,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/table_access_keys_stats.q.out b/ql/src/test/results/clientpositive/table_access_keys_stats.q.out index 7576b48..9015bab 100644 --- a/ql/src/test/results/clientpositive/table_access_keys_stats.q.out +++ b/ql/src/test/results/clientpositive/table_access_keys_stats.q.out @@ -22,7 +22,7 @@ SELECT key, count(1) FROM T1 GROUP BY key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key @@ -35,7 +35,7 @@ PREHOOK: query: SELECT key, val, count(1) FROM T1 GROUP BY key, val PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key,val @@ -50,7 +50,7 @@ SELECT key, count(1) FROM (SELECT key, val FROM T1) subq1 GROUP BY key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key @@ -63,7 +63,7 @@ PREHOOK: query: SELECT k, count(1) FROM (SELECT key as k, val as v FROM T1) subq PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key @@ -77,7 +77,7 @@ SELECT 1, key, count(1) FROM T1 GROUP BY 1, key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key @@ -90,7 +90,7 @@ PREHOOK: query: SELECT key, 1, val, count(1) FROM T1 GROUP BY key, 1, val PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key,val @@ -104,7 +104,7 @@ PREHOOK: query: SELECT key, 1, val, 2, count(1) FROM T1 GROUP BY key, 1, val, 2 PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key,val @@ -130,7 +130,7 @@ group by key + key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key @@ -148,11 +148,11 @@ SELECT key, count(1) as c FROM T1 GROUP BY key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key -Operator:GBY_10 +Operator:GBY_7 Table:default@t1 Keys:key @@ -218,7 +218,7 @@ group by key, constant, val PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key,val @@ -242,7 +242,7 @@ GROUP BY key, constant3, val PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key,val diff --git a/ql/src/test/results/clientpositive/temp_table.q.out b/ql/src/test/results/clientpositive/temp_table.q.out index e2987fe..e7cc27a 100644 --- a/ql/src/test/results/clientpositive/temp_table.q.out +++ b/ql/src/test/results/clientpositive/temp_table.q.out @@ -25,7 +25,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -132,7 +132,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -245,17 +245,17 @@ STAGE PLANS: Statistics: Num rows: 247 Data size: 2609 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 247 Data size: 2609 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + Statistics: Num rows: 247 Data size: 2609 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 247 Data size: 2609 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -305,37 +305,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: foo + alias: null-subquery1:u-subquery1:foo Statistics: Num rows: 247 Data size: 2609 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 247 Data size: 2609 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) TableScan - alias: bar + alias: null-subquery2:u-subquery2:bar Statistics: Num rows: 253 Data size: 2703 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 253 Data size: 2703 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE.value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 diff --git a/ql/src/test/results/clientpositive/temp_table_display_colstats_tbllvl.q.out b/ql/src/test/results/clientpositive/temp_table_display_colstats_tbllvl.q.out index cfa88ab..00a75aa 100644 --- a/ql/src/test/results/clientpositive/temp_table_display_colstats_tbllvl.q.out +++ b/ql/src/test/results/clientpositive/temp_table_display_colstats_tbllvl.q.out @@ -93,12 +93,15 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + outputColumnNames: _col0, _col1, _col2 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work @@ -202,26 +205,29 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - GlobalTableId: 0 + Select Operator + expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + outputColumnNames: _col0, _col1, _col2 + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 + NumFilesPerFileSink: 1 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types struct:struct:struct - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types struct:struct:struct + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Column Stats Work @@ -326,12 +332,15 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work diff --git a/ql/src/test/results/clientpositive/timestamp_ints_casts.q.out b/ql/src/test/results/clientpositive/timestamp_ints_casts.q.out index cc11e97..3789ae4 100644 --- a/ql/src/test/results/clientpositive/timestamp_ints_casts.q.out +++ b/ql/src/test/results/clientpositive/timestamp_ints_casts.q.out @@ -50,7 +50,7 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CAST( ctinyint AS TIMESTAMP) (type: timestamp), CAST( csmallint AS TIMESTAMP) (type: timestamp), CAST( cint AS TIMESTAMP) (type: timestamp), CAST( cbigint AS TIMESTAMP) (type: timestamp), CAST( cfloat AS TIMESTAMP) (type: timestamp), CAST( cdouble AS TIMESTAMP) (type: timestamp), CAST( cboolean1 AS TIMESTAMP) (type: timestamp), CAST( (cbigint * 0) AS TIMESTAMP) (type: timestamp), ctimestamp1 (type: timestamp), CAST( cstring1 AS TIMESTAMP) (type: timestamp), CAST( substr(cstring1, 1, 1) AS TIMESTAMP) (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cboolean1, _o__c7, ctimestamp1, cstring1, _o__c10 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -182,7 +182,7 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CAST( ctinyint AS TIMESTAMP) (type: timestamp), CAST( csmallint AS TIMESTAMP) (type: timestamp), CAST( cint AS TIMESTAMP) (type: timestamp), CAST( cbigint AS TIMESTAMP) (type: timestamp), CAST( cfloat AS TIMESTAMP) (type: timestamp), CAST( cdouble AS TIMESTAMP) (type: timestamp), CAST( cboolean1 AS TIMESTAMP) (type: timestamp), CAST( (cbigint * 0) AS TIMESTAMP) (type: timestamp), ctimestamp1 (type: timestamp), CAST( cstring1 AS TIMESTAMP) (type: timestamp), CAST( substr(cstring1, 1, 1) AS TIMESTAMP) (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cboolean1, _o__c7, ctimestamp1, cstring1, _o__c10 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -236,29 +236,29 @@ where cbigint % 250 = 0 POSTHOOK: type: QUERY POSTHOOK: Input: default@alltypesorc #### A masked pattern was here #### -1969-12-31 15:59:24 1969-12-31 15:56:40 NULL 1906-06-05 13:34:10 1969-12-31 15:59:24 1969-12-31 15:56:40 NULL 1969-12-31 16:00:00 1969-12-31 15:59:45.748 NULL NULL -1969-12-31 15:59:24 1969-12-31 15:56:40 NULL 2020-09-11 19:50:00 1969-12-31 15:59:24 1969-12-31 15:56:40 NULL 1969-12-31 16:00:00 1969-12-31 15:59:53.817 NULL NULL -1969-12-31 15:59:30 1969-12-31 15:56:40 NULL 2015-04-23 22:10:50 1969-12-31 15:59:30 1969-12-31 15:56:40 NULL 1969-12-31 16:00:00 1969-12-31 16:00:12.935 NULL NULL -1969-12-31 15:59:09 NULL 1994-07-07 10:09:31 2003-05-25 21:27:30 1969-12-31 15:59:09 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:08.451 NULL NULL -1969-12-31 15:59:09 NULL 1993-09-08 22:51:22 1908-10-29 07:05:50 1969-12-31 15:59:09 NULL 1969-12-31 16:00:01 1969-12-31 16:00:00 1969-12-31 16:00:08.451 NULL NULL -1969-12-31 16:00:20 1969-12-31 20:20:01 NULL 1958-07-07 21:05:50 1969-12-31 16:00:20 1969-12-31 20:20:01 NULL 1969-12-31 16:00:00 1969-12-31 15:59:45.129 NULL NULL -1969-12-31 15:59:22 1969-12-31 20:20:01 NULL 1911-02-07 01:30:00 1969-12-31 15:59:22 1969-12-31 20:20:01 NULL 1969-12-31 16:00:00 1969-12-31 15:59:58.614 NULL NULL -1969-12-31 15:59:55 1969-12-31 20:20:01 NULL 1989-05-28 20:33:20 1969-12-31 15:59:55 1969-12-31 20:20:01 NULL 1969-12-31 16:00:00 1969-12-31 16:00:04.679 NULL NULL -1969-12-31 16:00:48 1969-12-31 20:20:01 NULL 1944-10-18 03:23:20 1969-12-31 16:00:48 1969-12-31 20:20:01 NULL 1969-12-31 16:00:00 1969-12-31 15:59:50.235 NULL NULL -1969-12-31 16:00:08 NULL 1949-01-13 00:21:02 1940-06-26 15:47:30 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL -1969-12-31 16:00:08 NULL 1966-09-27 07:32:46 1928-05-26 10:07:30 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL -1969-12-31 16:00:08 NULL 1995-07-07 22:01:04 1997-07-05 20:58:20 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL -1969-12-31 16:00:08 NULL 1948-10-12 08:01:29 2020-05-04 04:20:50 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL -1969-12-31 16:00:08 NULL 1998-03-27 00:56:12 1910-12-27 06:10:00 1969-12-31 16:00:08 NULL 1969-12-31 16:00:01 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL -1969-12-31 16:00:08 NULL 1999-07-01 15:14:06 2008-03-13 02:07:30 1969-12-31 16:00:08 NULL 1969-12-31 16:00:01 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL -1969-12-31 15:59:01 1969-12-31 14:00:04 NULL 1919-02-22 13:13:20 1969-12-31 15:59:01 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:13.15 NULL NULL -1969-12-31 15:59:39 1969-12-31 14:00:04 NULL 2018-11-16 20:30:00 1969-12-31 15:59:39 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 15:59:55.9 NULL NULL -1969-12-31 15:59:00 1969-12-31 14:00:04 NULL 2018-01-18 14:32:30 1969-12-31 15:59:00 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 15:59:52.408 NULL NULL -1969-12-31 15:59:46 1969-12-31 14:00:04 NULL 1920-10-24 09:28:20 1969-12-31 15:59:46 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:11.065 NULL NULL -1969-12-31 16:00:59 1969-12-31 14:00:04 NULL 1933-12-12 05:05:00 1969-12-31 16:00:59 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:10.956 NULL NULL -1969-12-31 15:59:52 1969-12-31 14:00:04 NULL 1911-05-18 17:28:20 1969-12-31 15:59:52 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:03.136 NULL NULL -1969-12-31 16:00:05 1969-12-31 14:00:04 NULL 1937-10-25 22:48:20 1969-12-31 16:00:05 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:10.973 NULL NULL -1969-12-31 15:59:36 1969-12-31 14:00:04 NULL 1996-04-09 21:36:40 1969-12-31 15:59:36 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 15:59:53.145 NULL NULL -1969-12-31 15:59:10 1969-12-31 14:00:04 NULL 1937-04-28 15:05:50 1969-12-31 15:59:10 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 15:59:54.733 NULL NULL -1969-12-31 16:00:11 NULL 1967-12-14 19:06:58 2027-02-19 08:15:50 1969-12-31 16:00:11 NULL 1969-12-31 16:00:01 1969-12-31 16:00:00 1969-12-31 16:00:02.351 NULL NULL -1969-12-31 16:00:11 NULL 1959-05-16 04:19:43 2009-01-30 06:50:00 1969-12-31 16:00:11 NULL 1969-12-31 16:00:01 1969-12-31 16:00:00 1969-12-31 16:00:02.351 NULL NULL +1969-12-31 15:59:59.964 1969-12-31 15:59:59.8 NULL 1969-12-08 10:43:03.25 1969-12-31 15:59:24 1969-12-31 15:56:40 NULL 1969-12-31 16:00:00 1969-12-31 15:59:45.748 NULL NULL +1969-12-31 15:59:59.964 1969-12-31 15:59:59.8 NULL 1970-01-19 04:24:39 1969-12-31 15:59:24 1969-12-31 15:56:40 NULL 1969-12-31 16:00:00 1969-12-31 15:59:53.817 NULL NULL +1969-12-31 15:59:59.97 1969-12-31 15:59:59.8 NULL 1970-01-17 05:10:52.25 1969-12-31 15:59:30 1969-12-31 15:56:40 NULL 1969-12-31 16:00:00 1969-12-31 16:00:12.935 NULL NULL +1969-12-31 15:59:59.949 NULL 1970-01-09 14:53:20.971 1970-01-12 20:45:23.25 1969-12-31 15:59:09 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:08.451 NULL NULL +1969-12-31 15:59:59.949 NULL 1970-01-09 07:39:13.882 1969-12-09 07:45:32.75 1969-12-31 15:59:09 NULL 1969-12-31 16:00:00.001 1969-12-31 16:00:00 1969-12-31 16:00:08.451 NULL NULL +1969-12-31 16:00:00.02 1969-12-31 16:00:15.601 NULL 1969-12-27 11:19:26.75 1969-12-31 16:00:20 1969-12-31 20:20:01 NULL 1969-12-31 16:00:00 1969-12-31 15:59:45.129 NULL NULL +1969-12-31 15:59:59.962 1969-12-31 16:00:15.601 NULL 1969-12-10 03:41:51 1969-12-31 15:59:22 1969-12-31 20:20:01 NULL 1969-12-31 16:00:00 1969-12-31 15:59:58.614 NULL NULL +1969-12-31 15:59:59.995 1969-12-31 16:00:15.601 NULL 1970-01-07 18:06:56 1969-12-31 15:59:55 1969-12-31 20:20:01 NULL 1969-12-31 16:00:00 1969-12-31 16:00:04.679 NULL NULL +1969-12-31 16:00:00.048 1969-12-31 16:00:15.601 NULL 1969-12-22 11:03:59 1969-12-31 16:00:48 1969-12-31 20:20:01 NULL 1969-12-31 16:00:00 1969-12-31 15:59:50.235 NULL NULL +1969-12-31 16:00:00.008 NULL 1969-12-24 00:12:58.862 1969-12-20 21:16:47.25 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL +1969-12-31 16:00:00.008 NULL 1969-12-30 11:24:23.566 1969-12-16 11:20:17.25 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL +1969-12-31 16:00:00.008 NULL 1970-01-09 23:39:39.664 1970-01-10 17:09:21.5 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL +1969-12-31 16:00:00.008 NULL 1969-12-23 21:59:27.689 1970-01-19 01:16:31.25 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL +1969-12-31 16:00:00.008 NULL 1970-01-10 23:29:48.972 1969-12-10 02:41:39 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00.001 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL +1969-12-31 16:00:00.008 NULL 1970-01-11 10:34:27.246 1970-01-14 14:49:59.25 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00.001 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL +1969-12-31 15:59:59.941 1969-12-31 15:59:52.804 NULL 1969-12-13 02:11:50 1969-12-31 15:59:01 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:13.15 NULL NULL +1969-12-31 15:59:59.979 1969-12-31 15:59:52.804 NULL 1970-01-18 12:27:09 1969-12-31 15:59:39 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 15:59:55.9 NULL NULL +1969-12-31 15:59:59.94 1969-12-31 15:59:52.804 NULL 1970-01-18 05:11:54.75 1969-12-31 15:59:00 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 15:59:52.408 NULL NULL +1969-12-31 15:59:59.986 1969-12-31 15:59:52.804 NULL 1969-12-13 16:50:00.5 1969-12-31 15:59:46 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:11.065 NULL NULL +1969-12-31 16:00:00.059 1969-12-31 15:59:52.804 NULL 1969-12-18 11:57:25.5 1969-12-31 16:00:59 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:10.956 NULL NULL +1969-12-31 15:59:59.992 1969-12-31 15:59:52.804 NULL 1969-12-10 06:06:48.5 1969-12-31 15:59:52 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:03.136 NULL NULL +1969-12-31 16:00:00.005 1969-12-31 15:59:52.804 NULL 1969-12-19 21:53:12.5 1969-12-31 16:00:05 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:10.973 NULL NULL +1969-12-31 15:59:59.976 1969-12-31 15:59:52.804 NULL 1970-01-10 06:18:31 1969-12-31 15:59:36 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 15:59:53.145 NULL NULL +1969-12-31 15:59:59.95 1969-12-31 15:59:52.804 NULL 1969-12-19 17:33:32.75 1969-12-31 15:59:10 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 15:59:54.733 NULL NULL +1969-12-31 16:00:00.011 NULL 1969-12-30 22:03:04.018 1970-01-21 12:50:53.75 1969-12-31 16:00:11 NULL 1969-12-31 16:00:00.001 1969-12-31 16:00:00 1969-12-31 16:00:02.351 NULL NULL +1969-12-31 16:00:00.011 NULL 1969-12-27 18:49:09.583 1970-01-14 22:35:27 1969-12-31 16:00:11 NULL 1969-12-31 16:00:00.001 1969-12-31 16:00:00 1969-12-31 16:00:02.351 NULL NULL diff --git a/ql/src/test/results/clientpositive/truncate_column_list_bucket.q.out b/ql/src/test/results/clientpositive/truncate_column_list_bucket.q.out index 5ff6607..b193d10 100644 --- a/ql/src/test/results/clientpositive/truncate_column_list_bucket.q.out +++ b/ql/src/test/results/clientpositive/truncate_column_list_bucket.q.out @@ -155,7 +155,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 828 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '484' (type: string), value (type: string), '1' (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, part Statistics: Num rows: 8 Data size: 828 Basic stats: COMPLETE Column stats: NONE ListSink @@ -262,7 +262,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 828 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '0' (type: string), value (type: string), '1' (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, part Statistics: Num rows: 8 Data size: 828 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/type_cast_1.q.out b/ql/src/test/results/clientpositive/type_cast_1.q.out index 99aff5b..f60dc88 100644 --- a/ql/src/test/results/clientpositive/type_cast_1.q.out +++ b/ql/src/test/results/clientpositive/type_cast_1.q.out @@ -17,7 +17,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 5 (type: int) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 diff --git a/ql/src/test/results/clientpositive/type_widening.q.out b/ql/src/test/results/clientpositive/type_widening.q.out index e54ee13..719a73a 100644 --- a/ql/src/test/results/clientpositive/type_widening.q.out +++ b/ql/src/test/results/clientpositive/type_widening.q.out @@ -17,7 +17,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 0 (type: bigint) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 500 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 @@ -46,35 +46,43 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1:a-subquery1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 0 (type: bigint) - outputColumnNames: _col0 + outputColumnNames: numcol Statistics: Num rows: 500 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Union Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: bigint) - sort order: + + Select Operator + expressions: numcol (type: bigint) + outputColumnNames: numcol Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: numcol (type: bigint) + sort order: + + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE TableScan - alias: src + alias: null-subquery2:a-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 9223372036854775807 (type: bigint) - outputColumnNames: _col0 + outputColumnNames: numcol Statistics: Num rows: 500 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Union Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: bigint) - sort order: + + Select Operator + expressions: numcol (type: bigint) + outputColumnNames: numcol Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: numcol (type: bigint) + sort order: + + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: bigint) - outputColumnNames: _col0 + outputColumnNames: numcol Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/udaf_number_format.q.out b/ql/src/test/results/clientpositive/udaf_number_format.q.out index bc5e2c3..c201d84 100644 --- a/ql/src/test/results/clientpositive/udaf_number_format.q.out +++ b/ql/src/test/results/clientpositive/udaf_number_format.q.out @@ -24,29 +24,35 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 'a' (type: string) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 42500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: sum('a'), avg('a'), variance('a'), std('a') + aggregations: sum($f0), avg($f0), variance($f0), std($f0) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: double), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + value expressions: _col0 (type: double), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), avg(VALUE._col1), variance(VALUE._col2), std(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: double), $f1 (type: double), $f2 (type: double), $f3 (type: double) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/udf1.q.out b/ql/src/test/results/clientpositive/udf1.q.out index dffbccf..33d8753 100644 --- a/ql/src/test/results/clientpositive/udf1.q.out +++ b/ql/src/test/results/clientpositive/udf1.q.out @@ -54,7 +54,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: true (type: boolean), false (type: boolean), true (type: boolean), true (type: boolean), true (type: boolean), false (type: boolean), false (type: boolean), false (type: boolean), true (type: boolean), true (type: boolean), false (type: boolean), true (type: boolean), true (type: boolean), 'acc' (type: string), 'abc' (type: string), 'abb' (type: string), 'hive' (type: string), 'hadoop' (type: string), 'AaAbAcA' (type: string), false (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/udf2.q.out b/ql/src/test/results/clientpositive/udf2.q.out index d7a7bda..8ac27f8 100644 --- a/ql/src/test/results/clientpositive/udf2.q.out +++ b/ql/src/test/results/clientpositive/udf2.q.out @@ -34,7 +34,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '|' (type: string), trim(c1) (type: string), '|' (type: string), rtrim(c1) (type: string), '|' (type: string), ltrim(c1) (type: string), '|' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/udf3.q.out b/ql/src/test/results/clientpositive/udf3.q.out index 8b2ad31..a0357e7 100644 --- a/ql/src/test/results/clientpositive/udf3.q.out +++ b/ql/src/test/results/clientpositive/udf3.q.out @@ -27,9 +27,11 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: null (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Group By Operator - aggregations: count(null), sum(null), avg(null), min(null), max(null) + aggregations: count($f0), sum($f0), avg($f0), min($f0), max($f0) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE @@ -41,16 +43,20 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0), sum(VALUE._col1), avg(VALUE._col2), min(VALUE._col3), max(VALUE._col4) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: $f0, $f1, $f2, $f3, $f4 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: double), $f3 (type: int), $f4 (type: int) + outputColumnNames: $f0, $f1, $f2, $f3, $f4 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 Stage: Stage-0 Move Operator diff --git a/ql/src/test/results/clientpositive/udf4.q.out b/ql/src/test/results/clientpositive/udf4.q.out index 1e2ba3f..b805a46 100644 --- a/ql/src/test/results/clientpositive/udf4.q.out +++ b/ql/src/test/results/clientpositive/udf4.q.out @@ -78,7 +78,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1.0 (type: double), 2.0 (type: double), -2.0 (type: double), 1 (type: bigint), 1 (type: bigint), -2 (type: bigint), 1.0 (type: double), null (type: double), 0.0 (type: double), 1 (type: bigint), 2 (type: bigint), -1 (type: bigint), 1 (type: bigint), rand(3) (type: double), 3 (type: int), -3 (type: int), 3 (type: int), -1 (type: int), -2 (type: int), -2 (type: tinyint), -2 (type: smallint), -2 (type: bigint), 0 (type: tinyint), 0 (type: smallint), 0 (type: int), 0 (type: bigint), 3 (type: tinyint), 3 (type: smallint), 3 (type: int), 3 (type: bigint), 2 (type: tinyint), 2 (type: smallint), 2 (type: int), 2 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20, _o__c21, _o__c22, _o__c23, _o__c24, _o__c25, _o__c26, _o__c27, _o__c28, _o__c29, _o__c30, _o__c31, _o__c32, _o__c33 Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/udf5.q.out b/ql/src/test/results/clientpositive/udf5.q.out index 860ebcb..620c3e4 100644 --- a/ql/src/test/results/clientpositive/udf5.q.out +++ b/ql/src/test/results/clientpositive/udf5.q.out @@ -34,7 +34,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '2008-11-11 15:32:20' (type: string), '2008-11-11' (type: string), 1 (type: int), 11 (type: int), 2008 (type: int), 1 (type: int), 11 (type: int), 2008 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7 Statistics: Num rows: 1 Data size: 221 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -66,7 +66,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '01/13/10 11:57:40' (type: string), '2010-01-13 11:57:40' (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _o__c0, _o__c1 Statistics: Num rows: 1 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE ListSink diff --git a/ql/src/test/results/clientpositive/udf6.q.out b/ql/src/test/results/clientpositive/udf6.q.out index 0b92bd5..adee5a2 100644 --- a/ql/src/test/results/clientpositive/udf6.q.out +++ b/ql/src/test/results/clientpositive/udf6.q.out @@ -34,7 +34,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1 (type: int) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE ListSink @@ -76,7 +76,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1 (type: int), 2 (type: int), 2 (type: int), 'a' (type: string), 0.1 (type: double), 2 (type: bigint), 126 (type: tinyint), 128 (type: smallint), 128 (type: int), 1.0 (type: double), '128' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10 Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: COMPLETE ListSink diff --git a/ql/src/test/results/clientpositive/udf7.q.out b/ql/src/test/results/clientpositive/udf7.q.out index b15ccaf..461d4f3 100644 --- a/ql/src/test/results/clientpositive/udf7.q.out +++ b/ql/src/test/results/clientpositive/udf7.q.out @@ -48,7 +48,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1.098612288668 (type: double), null (type: double), null (type: double), 1.098612288668 (type: double), null (type: double), null (type: double), 1.584962500721 (type: double), null (type: double), null (type: double), 0.47712125472 (type: double), null (type: double), null (type: double), 1.584962500721 (type: double), null (type: double), null (type: double), null (type: double), -1.0 (type: double), 7.389056098931 (type: double), 8.0 (type: double), 8.0 (type: double), 0.125 (type: double), 8.0 (type: double), 2.0 (type: double), NaN (type: double), 1.0 (type: double), 1.0 (type: double), 8.0 (type: double), 8.0 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20, _o__c21, _o__c22, _o__c23, _o__c24, _o__c25, _o__c26, _o__c27 Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE ListSink diff --git a/ql/src/test/results/clientpositive/udf8.q.out b/ql/src/test/results/clientpositive/udf8.q.out index 8276ba9..4c1c0bf 100644 --- a/ql/src/test/results/clientpositive/udf8.q.out +++ b/ql/src/test/results/clientpositive/udf8.q.out @@ -43,10 +43,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: string) - outputColumnNames: _col0 + outputColumnNames: c1 Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), sum(_col0), count(_col0) + aggregations: avg(c1), sum(c1), count(c1) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -58,15 +58,19 @@ STAGE PLANS: Group By Operator aggregations: avg(VALUE._col0), sum(VALUE._col1), count(VALUE._col2) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: double), $f1 (type: double), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/udf9.q.out b/ql/src/test/results/clientpositive/udf9.q.out index 5c12229..b6bc0a5 100644 --- a/ql/src/test/results/clientpositive/udf9.q.out +++ b/ql/src/test/results/clientpositive/udf9.q.out @@ -36,7 +36,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: -1 (type: int), 2 (type: int), 32 (type: int), -1 (type: int), '2009-01-01' (type: string), '2009-12-31' (type: string), '2008-03-01' (type: string), '2009-03-02' (type: string), '2008-02-28' (type: string), '2009-02-27' (type: string), '2008-12-31' (type: string), '2008-01-02' (type: string), '2008-02-26' (type: string), '2009-02-26' (type: string), '2006-02-28' (type: string), '2005-02-28' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/udf_10_trims.q.out b/ql/src/test/results/clientpositive/udf_10_trims.q.out index 2f79723..d2996b8 100644 --- a/ql/src/test/results/clientpositive/udf_10_trims.q.out +++ b/ql/src/test/results/clientpositive/udf_10_trims.q.out @@ -40,7 +40,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'abc' (type: string) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/udf_between.q.out b/ql/src/test/results/clientpositive/udf_between.q.out index efe6615..f9dac01 100644 --- a/ql/src/test/results/clientpositive/udf_between.q.out +++ b/ql/src/test/results/clientpositive/udf_between.q.out @@ -28,7 +28,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 @@ -83,7 +83,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 @@ -135,7 +135,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 @@ -168,7 +168,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 diff --git a/ql/src/test/results/clientpositive/udf_case_column_pruning.q.out b/ql/src/test/results/clientpositive/udf_case_column_pruning.q.out index a9bfd24..f990892 100644 --- a/ql/src/test/results/clientpositive/udf_case_column_pruning.q.out +++ b/ql/src/test/results/clientpositive/udf_case_column_pruning.q.out @@ -35,40 +35,40 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: CASE (_col0) WHEN ('1') THEN (2) WHEN ('3') THEN (4) ELSE (5) END (type: int) - outputColumnNames: _col0 + expressions: CASE (key) WHEN ('1') THEN (2) WHEN ('3') THEN (4) ELSE (5) END (type: int) + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -82,13 +82,13 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: key (type: int) sort order: + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 diff --git a/ql/src/test/results/clientpositive/udf_concat_ws.q.out b/ql/src/test/results/clientpositive/udf_concat_ws.q.out index ea2d703..5eeada6 100644 --- a/ql/src/test/results/clientpositive/udf_concat_ws.q.out +++ b/ql/src/test/results/clientpositive/udf_concat_ws.q.out @@ -55,7 +55,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: concat_ws(c1, c2, c3) (type: string), concat_ws(',', c1, c2, c3) (type: string), concat_ws(null, c1, c2, c3) (type: string), concat_ws('**', c1, null, c3) (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3 Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/udf_count.q.out b/ql/src/test/results/clientpositive/udf_count.q.out index c9a596f..3ddb6cd 100644 --- a/ql/src/test/results/clientpositive/udf_count.q.out +++ b/ql/src/test/results/clientpositive/udf_count.q.out @@ -29,10 +29,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -44,15 +44,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -86,11 +90,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0) - keys: _col0 (type: string) + aggregations: count(DISTINCT key) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -102,15 +106,19 @@ STAGE PLANS: Group By Operator aggregations: count(DISTINCT KEY._col0:0._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -144,11 +152,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0, _col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT key, value) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -160,15 +168,19 @@ STAGE PLANS: Group By Operator aggregations: count(DISTINCT KEY._col0:0._col0, KEY._col0:0._col1) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -201,7 +213,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -215,15 +227,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -256,9 +272,11 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -270,15 +288,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/udf_example_add.q.out b/ql/src/test/results/clientpositive/udf_example_add.q.out index 7916679..5b6e8f6 100644 --- a/ql/src/test/results/clientpositive/udf_example_add.q.out +++ b/ql/src/test/results/clientpositive/udf_example_add.q.out @@ -37,7 +37,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 3 (type: int), 6 (type: int), 10 (type: int), 3.3000000000000003 (type: double), 6.6 (type: double), 11.0 (type: double), 10.4 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6 Statistics: Num rows: 500 Data size: 22000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 diff --git a/ql/src/test/results/clientpositive/udf_explode.q.out b/ql/src/test/results/clientpositive/udf_explode.q.out index 21f5aa2..47d6748 100644 --- a/ql/src/test/results/clientpositive/udf_explode.q.out +++ b/ql/src/test/results/clientpositive/udf_explode.q.out @@ -133,20 +133,24 @@ STAGE PLANS: UDTF Operator Statistics: Num rows: 500 Data size: 28000 Basic stats: COMPLETE Column stats: COMPLETE function name: explode - Group By Operator - aggregations: count(1) - keys: col (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + Select Operator + expressions: col (type: int) + outputColumnNames: col + Statistics: Num rows: 500 Data size: 28000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(1) + keys: col (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: bigint) - auto parallelism: false + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -204,27 +208,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1 - columns.types int:bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1 + columns.types int:bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -407,20 +415,24 @@ STAGE PLANS: UDTF Operator Statistics: Num rows: 500 Data size: 259500 Basic stats: COMPLETE Column stats: COMPLETE function name: explode - Group By Operator - aggregations: count(1) - keys: key (type: int), value (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 259500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(1) + keys: key (type: int), value (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col2 (type: bigint) - auto parallelism: false + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col2 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -478,27 +490,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types int:string:bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types int:string:bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/udf_find_in_set.q.out b/ql/src/test/results/clientpositive/udf_find_in_set.q.out index 9d01f7b..2142c8e 100644 --- a/ql/src/test/results/clientpositive/udf_find_in_set.q.out +++ b/ql/src/test/results/clientpositive/udf_find_in_set.q.out @@ -33,7 +33,7 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: find_in_set(key, concat(key, ',', value)) (type: int) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/udf_get_json_object.q.out b/ql/src/test/results/clientpositive/udf_get_json_object.q.out index fb95700..e6cb70a 100644 --- a/ql/src/test/results/clientpositive/udf_get_json_object.q.out +++ b/ql/src/test/results/clientpositive/udf_get_json_object.q.out @@ -59,7 +59,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 644 Basic stats: COMPLETE Column stats: NONE Select Operator #### A masked pattern was here #### - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 1 Data size: 644 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/udf_hour.q.out b/ql/src/test/results/clientpositive/udf_hour.q.out index cf7f78b..46a8dd2 100644 --- a/ql/src/test/results/clientpositive/udf_hour.q.out +++ b/ql/src/test/results/clientpositive/udf_hour.q.out @@ -40,7 +40,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 13 (type: int), 13 (type: int), null (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _o__c0, _o__c1, _o__c2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/udf_in_file.q.out b/ql/src/test/results/clientpositive/udf_in_file.q.out index 6d2c84b..731f566 100644 --- a/ql/src/test/results/clientpositive/udf_in_file.q.out +++ b/ql/src/test/results/clientpositive/udf_in_file.q.out @@ -60,7 +60,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: in_file(str_val, '../../data/files/test2.dat') (type: boolean), in_file(ch_val, '../../data/files/test2.dat') (type: boolean), in_file(vch_val, '../../data/files/test2.dat') (type: boolean), in_file(str_val_neg, '../../data/files/test2.dat') (type: boolean), in_file(ch_val_neg, '../../data/files/test2.dat') (type: boolean), in_file(vch_val_neg, '../../data/files/test2.dat') (type: boolean), in_file('303', '../../data/files/test2.dat') (type: boolean), in_file('304', '../../data/files/test2.dat') (type: boolean), in_file(null, '../../data/files/test2.dat') (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 diff --git a/ql/src/test/results/clientpositive/udf_isnull_isnotnull.q.out b/ql/src/test/results/clientpositive/udf_isnull_isnotnull.q.out index b59a5b9..ae7a012 100644 --- a/ql/src/test/results/clientpositive/udf_isnull_isnotnull.q.out +++ b/ql/src/test/results/clientpositive/udf_isnull_isnotnull.q.out @@ -45,7 +45,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: true (type: boolean), true (type: boolean), true (type: boolean) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _o__c0, _o__c1, _o__c2 Statistics: Num rows: 500 Data size: 6000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 diff --git a/ql/src/test/results/clientpositive/udf_length.q.out b/ql/src/test/results/clientpositive/udf_length.q.out index 0dc39ea..9f5d280 100644 --- a/ql/src/test/results/clientpositive/udf_length.q.out +++ b/ql/src/test/results/clientpositive/udf_length.q.out @@ -42,7 +42,7 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: length(value) (type: int) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -190,7 +190,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: length(name) (type: int) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/udf_like.q.out b/ql/src/test/results/clientpositive/udf_like.q.out index 8ffcf9b..b38501f 100644 --- a/ql/src/test/results/clientpositive/udf_like.q.out +++ b/ql/src/test/results/clientpositive/udf_like.q.out @@ -39,7 +39,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: true (type: boolean), false (type: boolean), true (type: boolean), true (type: boolean), false (type: boolean), false (type: boolean), false (type: boolean), false (type: boolean), true (type: boolean), false (type: boolean), false (type: boolean), false (type: boolean), false (type: boolean), true (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/udf_lower.q.out b/ql/src/test/results/clientpositive/udf_lower.q.out index 0d662ac..20833f4 100644 --- a/ql/src/test/results/clientpositive/udf_lower.q.out +++ b/ql/src/test/results/clientpositive/udf_lower.q.out @@ -34,7 +34,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'abc 123' (type: string), 'ABC 123' (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _o__c0, _o__c1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/udf_max.q.out b/ql/src/test/results/clientpositive/udf_max.q.out index 8535752..4575913 100644 --- a/ql/src/test/results/clientpositive/udf_max.q.out +++ b/ql/src/test/results/clientpositive/udf_max.q.out @@ -20,7 +20,7 @@ FROM src POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -{"col1":498,"col2":"val_498"} {"col1":"98","col2":"val_98"} +{"col1":498,"col2":"val_498"} {"col1":"498","col2":"val_498"} PREHOOK: query: SELECT max(struct(CAST(key as INT), value)), max(struct(key, value)) FROM src @@ -46,7 +46,7 @@ FROM src POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -{"col1":498,"col2":"val_498"} {"col1":"98","col2":"val_98"} +{"col1":498,"col2":"val_498"} {"col1":"498","col2":"val_498"} PREHOOK: query: SELECT max(struct(CAST(key as INT), value)), max(struct(key, value)) FROM src diff --git a/ql/src/test/results/clientpositive/udf_minute.q.out b/ql/src/test/results/clientpositive/udf_minute.q.out index 3af42c4..c6d5027 100644 --- a/ql/src/test/results/clientpositive/udf_minute.q.out +++ b/ql/src/test/results/clientpositive/udf_minute.q.out @@ -40,7 +40,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 14 (type: int), 14 (type: int), null (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _o__c0, _o__c1, _o__c2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/udf_notequal.q.out b/ql/src/test/results/clientpositive/udf_notequal.q.out index 25162da..b2a1404 100644 --- a/ql/src/test/results/clientpositive/udf_notequal.q.out +++ b/ql/src/test/results/clientpositive/udf_notequal.q.out @@ -46,7 +46,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink @@ -587,7 +587,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/udf_parse_url.q.out b/ql/src/test/results/clientpositive/udf_parse_url.q.out index 5ea8f40..93f54eb 100644 --- a/ql/src/test/results/clientpositive/udf_parse_url.q.out +++ b/ql/src/test/results/clientpositive/udf_parse_url.q.out @@ -61,7 +61,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'facebook.com' (type: string), '/path1/p.php' (type: string), 'k1=v1&k2=v2' (type: string), 'Ref1' (type: string), 'v2' (type: string), 'v1' (type: string), null (type: string), '/path1/p.php?k1=v1&k2=v2' (type: string), 'http' (type: string), null (type: string), 'facebook.com' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/udf_reflect2.q.out b/ql/src/test/results/clientpositive/udf_reflect2.q.out index 6c22657..b4ca535 100644 --- a/ql/src/test/results/clientpositive/udf_reflect2.q.out +++ b/ql/src/test/results/clientpositive/udf_reflect2.q.out @@ -316,12 +316,12 @@ STAGE PLANS: limit: 5 Processor Tree: TableScan - alias: src + alias: a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: UDFToInteger(key) (type: int), reflect2(UDFToInteger(key),'byteValue') (type: tinyint), reflect2(UDFToInteger(key),'shortValue') (type: smallint), reflect2(UDFToInteger(key),'intValue') (type: int), reflect2(UDFToInteger(key),'longValue') (type: bigint), reflect2(UDFToInteger(key),'floatValue') (type: float), reflect2(UDFToInteger(key),'doubleValue') (type: double), reflect2(UDFToInteger(key),'toString') (type: string), value (type: string), reflect2(value,'concat','_concat') (type: string), reflect2(value,'contains','86') (type: boolean), reflect2(value,'startsWith','v') (type: boolean), reflect2(value,'endsWith','6') (type: boolean), reflect2(value,'equals','val_86') (type: boolean), reflect2(value,'equalsIgnoreCase','VAL_86') (type: boolean), reflect2(value,'getBytes') (type: binary), reflect2(value,'indexOf','1') (type: int), reflect2(value,'lastIndexOf','1') (type: int), reflect2(value,'replace','val','VALUE') (type: string), reflect2(value,'substring',1) (type: string), reflect2(value,'substring',1,5) (type: string), reflect2(value,'toUpperCase') (type: string), reflect2(value,'trim') (type: string), 2013-02-15 19:41:20.0 (type: timestamp), 113 (type: int), 1 (type: int), 5 (type: int), 19 (type: int), 41 (type: int), 20 (type: int), 1360986080000 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30 + outputColumnNames: key, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, value, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20, _o__c21, _o__c22, ts, _o__c24, _o__c25, _o__c26, _o__c27, _o__c28, _o__c29, _o__c30 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 diff --git a/ql/src/test/results/clientpositive/udf_reverse.q.out b/ql/src/test/results/clientpositive/udf_reverse.q.out index 4fee27f..04436df 100644 --- a/ql/src/test/results/clientpositive/udf_reverse.q.out +++ b/ql/src/test/results/clientpositive/udf_reverse.q.out @@ -42,7 +42,7 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: reverse(value) (type: string) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/udf_second.q.out b/ql/src/test/results/clientpositive/udf_second.q.out index 4ee919a..8e20776b1 100644 --- a/ql/src/test/results/clientpositive/udf_second.q.out +++ b/ql/src/test/results/clientpositive/udf_second.q.out @@ -40,7 +40,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 15 (type: int), 15 (type: int), null (type: int) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _o__c0, _o__c1, _o__c2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/udf_to_unix_timestamp.q.out b/ql/src/test/results/clientpositive/udf_to_unix_timestamp.q.out index ce82461..4db46e1 100644 --- a/ql/src/test/results/clientpositive/udf_to_unix_timestamp.q.out +++ b/ql/src/test/results/clientpositive/udf_to_unix_timestamp.q.out @@ -100,14 +100,14 @@ STAGE PLANS: limit: -1 Processor Tree: TableScan - alias: src + alias: a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (unix_timestamp(key) > 10) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE ListSink @@ -124,14 +124,14 @@ STAGE PLANS: limit: -1 Processor Tree: TableScan - alias: src + alias: a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (to_unix_timestamp(key) > 10) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE ListSink diff --git a/ql/src/test/results/clientpositive/udtf_explode.q.out b/ql/src/test/results/clientpositive/udtf_explode.q.out index f89ec97..6fd2b8c 100644 --- a/ql/src/test/results/clientpositive/udtf_explode.q.out +++ b/ql/src/test/results/clientpositive/udtf_explode.q.out @@ -200,29 +200,33 @@ STAGE PLANS: Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1 - columns.types int,bigint - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator + aggregations: count(1) + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1 + columns.types int,bigint + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -270,27 +274,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1 - columns.types int:bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1 + columns.types int:bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -510,29 +518,33 @@ STAGE PLANS: Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types int,string,bigint - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator + aggregations: count(1) + keys: _col0 (type: int), _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types int,string,bigint + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -580,27 +592,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types int:string:bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types int:string:bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/udtf_json_tuple.q.out b/ql/src/test/results/clientpositive/udtf_json_tuple.q.out index 6e60553..61becaa 100644 --- a/ql/src/test/results/clientpositive/udtf_json_tuple.q.out +++ b/ql/src/test/results/clientpositive/udtf_json_tuple.q.out @@ -355,12 +355,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 4 Data size: 157 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 157 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce diff --git a/ql/src/test/results/clientpositive/udtf_parse_url_tuple.q.out b/ql/src/test/results/clientpositive/udtf_parse_url_tuple.q.out index eb7a153..9f82a61 100644 --- a/ql/src/test/results/clientpositive/udtf_parse_url_tuple.q.out +++ b/ql/src/test/results/clientpositive/udtf_parse_url_tuple.q.out @@ -373,13 +373,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 4 Data size: 141 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 4 Data size: 141 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 141 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/union.q.out b/ql/src/test/results/clientpositive/union.q.out index b00b0b6..5d97fef 100644 --- a/ql/src/test/results/clientpositive/union.q.out +++ b/ql/src/test/results/clientpositive/union.q.out @@ -34,43 +34,51 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1:unioninput-subquery1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: src + alias: null-subquery2:unioninput-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) > 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-6 Conditional Operator diff --git a/ql/src/test/results/clientpositive/union10.q.out b/ql/src/test/results/clientpositive/union10.q.out index 417ae27..9938a8d 100644 --- a/ql/src/test/results/clientpositive/union10.q.out +++ b/ql/src/test/results/clientpositive/union10.q.out @@ -48,12 +48,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1-subquery1:unionsrc-subquery1-subquery1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -65,11 +67,11 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst1' (type: string), _col0 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: 'tst1' (type: string), $f0 (type: bigint) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -85,7 +87,7 @@ STAGE PLANS: Union Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + expressions: key (type: char(4)), UDFToInteger(value) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -100,7 +102,7 @@ STAGE PLANS: Union Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + expressions: key (type: char(4)), UDFToInteger(value) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -115,7 +117,7 @@ STAGE PLANS: Union Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + expressions: key (type: char(4)), UDFToInteger(value) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -183,12 +185,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1-subquery2:unionsrc-subquery1-subquery2:s2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -200,11 +204,11 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst2' (type: string), _col0 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: 'tst2' (type: string), $f0 (type: bigint) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -217,12 +221,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery2:unionsrc-subquery2:s3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -234,11 +240,11 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst3' (type: string), _col0 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: 'tst3' (type: string), $f0 (type: bigint) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/union11.q.out b/ql/src/test/results/clientpositive/union11.q.out index 0d0b8fa..e7d04fc 100644 --- a/ql/src/test/results/clientpositive/union11.q.out +++ b/ql/src/test/results/clientpositive/union11.q.out @@ -30,29 +30,24 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1-subquery1:unionsrc-subquery1-subquery1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator expressions: 'tst1' (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: key + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE File Output Operator compressed: false table: @@ -65,91 +60,102 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator + expressions: key (type: char(4)), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: char(4)) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: char(4)) + sort order: + + Map-reduce partition columns: _col0 (type: char(4)) + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator + expressions: key (type: char(4)), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: char(4)) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: char(4)) + sort order: + + Map-reduce partition columns: _col0 (type: char(4)) + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator + expressions: key (type: char(4)), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: char(4)) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: char(4)) + sort order: + + Map-reduce partition columns: _col0 (type: char(4)) + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) + keys: KEY._col0 (type: char(4)) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: $f0 (type: char(4)), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1-subquery2:unionsrc-subquery1-subquery2:s2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator expressions: 'tst2' (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: key + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE File Output Operator compressed: false table: @@ -161,29 +167,24 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery2:unionsrc-subquery2:s3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator expressions: 'tst3' (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: key + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/union12.q.out b/ql/src/test/results/clientpositive/union12.q.out index ee56f15..05877c7 100644 --- a/ql/src/test/results/clientpositive/union12.q.out +++ b/ql/src/test/results/clientpositive/union12.q.out @@ -48,12 +48,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1-subquery1:unionsrc-subquery1-subquery1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -65,11 +67,11 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst1' (type: string), _col0 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: 'tst1' (type: string), $f0 (type: bigint) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -85,7 +87,7 @@ STAGE PLANS: Union Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + expressions: key (type: char(4)), UDFToInteger(value) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -100,7 +102,7 @@ STAGE PLANS: Union Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + expressions: key (type: char(4)), UDFToInteger(value) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -115,7 +117,7 @@ STAGE PLANS: Union Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + expressions: key (type: char(4)), UDFToInteger(value) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -183,12 +185,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s2 + alias: null-subquery1-subquery2:unionsrc-subquery1-subquery2:s2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -200,11 +204,11 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst2' (type: string), _col0 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: 'tst2' (type: string), $f0 (type: bigint) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -217,12 +221,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s3 + alias: null-subquery2:unionsrc-subquery2:s3 Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 1000 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -234,11 +240,11 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst3' (type: string), _col0 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: 'tst3' (type: string), $f0 (type: bigint) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/union13.q.out b/ql/src/test/results/clientpositive/union13.q.out index 04079fc..bf5bf27 100644 --- a/ql/src/test/results/clientpositive/union13.q.out +++ b/ql/src/test/results/clientpositive/union13.q.out @@ -21,37 +21,45 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1:unionsrc-subquery1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: s1 + alias: null-subquery2:unionsrc-subquery2:s2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/union14.q.out b/ql/src/test/results/clientpositive/union14.q.out index 7a7e938..90b009c 100644 --- a/ql/src/test/results/clientpositive/union14.q.out +++ b/ql/src/test/results/clientpositive/union14.q.out @@ -26,29 +26,24 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery2:unionsrc-subquery2:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator expressions: 'tst1' (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: key + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE File Output Operator compressed: false table: @@ -60,55 +55,67 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s2 + alias: null-subquery1:unionsrc-subquery1:s2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + TableScan + Union + Statistics: Num rows: 26 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) - TableScan - Union - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/union15.q.out b/ql/src/test/results/clientpositive/union15.q.out index 148f25f..55e2ae9 100644 --- a/ql/src/test/results/clientpositive/union15.q.out +++ b/ql/src/test/results/clientpositive/union15.q.out @@ -28,29 +28,24 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1-subquery1:unionsrc-subquery1-subquery1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator expressions: 'tst1' (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: key + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE File Output Operator compressed: false table: @@ -63,75 +58,91 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 51 Data size: 470 Basic stats: COMPLETE Column stats: PARTIAL - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: bigint) - TableScan - alias: s2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 51 Data size: 470 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 51 Data size: 382 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 51 Data size: 204 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: bigint) TableScan - alias: s2 + alias: null-subquery1-subquery2:unionsrc-subquery1-subquery2:s2 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 51 Data size: 470 Basic stats: COMPLETE Column stats: PARTIAL - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: bigint) + Statistics: Num rows: 51 Data size: 382 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 51 Data size: 204 Basic stats: COMPLETE Column stats: PARTIAL + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + value expressions: _col1 (type: bigint) + TableScan + alias: null-subquery2:unionsrc-subquery2:s3 + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 51 Data size: 382 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 51 Data size: 204 Basic stats: COMPLETE Column stats: PARTIAL + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/union16.q.out b/ql/src/test/results/clientpositive/union16.q.out index 9f7dd68..fbef364 100644 --- a/ql/src/test/results/clientpositive/union16.q.out +++ b/ql/src/test/results/clientpositive/union16.q.out @@ -73,18 +73,20 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -93,18 +95,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -113,18 +117,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -133,18 +139,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -153,18 +161,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -173,18 +183,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -193,18 +205,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -213,18 +227,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -233,18 +249,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -253,18 +271,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -273,18 +293,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -293,18 +315,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -313,18 +337,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -333,18 +359,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -353,18 +381,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -373,18 +403,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -393,18 +425,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -413,18 +447,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -433,18 +469,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -453,18 +491,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -473,18 +513,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -493,18 +535,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -513,18 +557,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery1-subquery2:src-subquery1-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -533,18 +579,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery1-subquery2:src-subquery1-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -553,18 +601,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src + alias: null-subquery2:src-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 12500 Data size: 132800 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -576,15 +626,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/union17.q.out b/ql/src/test/results/clientpositive/union17.q.out index 62245c4..84306fe 100644 --- a/ql/src/test/results/clientpositive/union17.q.out +++ b/ql/src/test/results/clientpositive/union17.q.out @@ -84,37 +84,9 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL - Group By Operator - aggregations: count(DISTINCT substr(_col1, 5)) - keys: _col0 (type: string), substr(_col1, 5) (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 70000 Basic stats: COMPLETE Column stats: PARTIAL - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 70000 Basic stats: COMPLETE Column stats: PARTIAL - Group By Operator - aggregations: count(DISTINCT substr(_col1, 5)) - keys: _col0 (type: string), _col1 (type: string), substr(_col1, 5) (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 116000 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TableScan - alias: s2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Union + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: count(DISTINCT substr(_col1, 5)) @@ -127,6 +99,10 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 70000 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: count(DISTINCT substr(_col1, 5)) keys: _col0 (type: string), _col1 (type: string), substr(_col1, 5) (type: string) @@ -139,6 +115,46 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TableScan + alias: s2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL + Group By Operator + aggregations: count(DISTINCT substr(_col1, 5)) + keys: _col0 (type: string), substr(_col1, 5) (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 70000 Basic stats: COMPLETE Column stats: PARTIAL + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 70000 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL + Group By Operator + aggregations: count(DISTINCT substr(_col1, 5)) + keys: _col0 (type: string), _col1 (type: string), substr(_col1, 5) (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 116000 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0) @@ -146,14 +162,18 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 Stage: Stage-0 Move Operator @@ -184,14 +204,18 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: PARTIAL + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest2 Stage: Stage-1 Move Operator diff --git a/ql/src/test/results/clientpositive/union18.q.out b/ql/src/test/results/clientpositive/union18.q.out index 5993280..df7ed61 100644 --- a/ql/src/test/results/clientpositive/union18.q.out +++ b/ql/src/test/results/clientpositive/union18.q.out @@ -95,14 +95,18 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false - Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 501 Data size: 136272 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 501 Data size: 136272 Basic stats: COMPLETE Column stats: PARTIAL + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 Select Operator expressions: _col0 (type: string), _col1 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 @@ -124,14 +128,18 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false - Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 501 Data size: 136272 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 501 Data size: 136272 Basic stats: COMPLETE Column stats: PARTIAL + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 Select Operator expressions: _col0 (type: string), _col1 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 diff --git a/ql/src/test/results/clientpositive/union19.q.out b/ql/src/test/results/clientpositive/union19.q.out index 89d9c6d..f363df4 100644 --- a/ql/src/test/results/clientpositive/union19.q.out +++ b/ql/src/test/results/clientpositive/union19.q.out @@ -85,18 +85,22 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + value expressions: _col1 (type: bigint) Select Operator expressions: _col0 (type: string), _col1 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 @@ -118,18 +122,22 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + value expressions: _col1 (type: bigint) Select Operator expressions: _col0 (type: string), _col1 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 @@ -149,14 +157,18 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 Stage: Stage-0 Move Operator diff --git a/ql/src/test/results/clientpositive/union2.q.out b/ql/src/test/results/clientpositive/union2.q.out index 69559a4..d4ba96a 100644 --- a/ql/src/test/results/clientpositive/union2.q.out +++ b/ql/src/test/results/clientpositive/union2.q.out @@ -21,18 +21,20 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1:unionsrc-subquery1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -41,18 +43,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: s1 + alias: null-subquery2:unionsrc-subquery2:s2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -64,15 +68,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/union20.q.out b/ql/src/test/results/clientpositive/union20.q.out index 3f0eeed..66dee7b 100644 --- a/ql/src/test/results/clientpositive/union20.q.out +++ b/ql/src/test/results/clientpositive/union20.q.out @@ -37,12 +37,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1:unionsrc1-subquery1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -54,11 +56,11 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst1' (type: string), UDFToString(_col0) (type: string) - outputColumnNames: _col0, _col1 + expressions: 'tst1' (type: string), UDFToString($f0) (type: string) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -74,83 +76,89 @@ STAGE PLANS: Union Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: s1 + alias: null-subquery2:unionsrc1-subquery2:s2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 10.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan Union Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: s1 + alias: null-subquery2:unionsrc2-subquery2:s4 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) < 10.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 27889 Data size: 15171616 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 Statistics: Num rows: 27889 Data size: 15171616 Basic stats: COMPLETE Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 27889 Data size: 15171616 Basic stats: COMPLETE Column stats: PARTIAL + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1:unionsrc2-subquery1:s3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -162,11 +170,11 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst1' (type: string), UDFToString(_col0) (type: string) - outputColumnNames: _col0, _col1 + expressions: 'tst1' (type: string), UDFToString($f0) (type: string) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/union21.q.out b/ql/src/test/results/clientpositive/union21.q.out index 8267e9e..b8d10fe 100644 --- a/ql/src/test/results/clientpositive/union21.q.out +++ b/ql/src/test/results/clientpositive/union21.q.out @@ -51,18 +51,22 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 42500 Basic stats: COMPLETE Column stats: COMPLETE Union Statistics: Num rows: 1522 Data size: 59264 Basic stats: COMPLETE Column stats: PARTIAL - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1522 Data size: 59264 Basic stats: COMPLETE Column stats: PARTIAL + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL + value expressions: _col1 (type: bigint) TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -72,18 +76,22 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1522 Data size: 59264 Basic stats: COMPLETE Column stats: PARTIAL - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1522 Data size: 59264 Basic stats: COMPLETE Column stats: PARTIAL + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL + value expressions: _col1 (type: bigint) TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -93,18 +101,22 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1522 Data size: 59264 Basic stats: COMPLETE Column stats: PARTIAL - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1522 Data size: 59264 Basic stats: COMPLETE Column stats: PARTIAL + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL + value expressions: _col1 (type: bigint) TableScan alias: src_thrift Statistics: Num rows: 11 Data size: 3070 Basic stats: COMPLETE Column stats: NONE @@ -114,18 +126,22 @@ STAGE PLANS: Statistics: Num rows: 11 Data size: 3070 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1522 Data size: 59264 Basic stats: COMPLETE Column stats: PARTIAL - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1522 Data size: 59264 Basic stats: COMPLETE Column stats: PARTIAL + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL + value expressions: _col1 (type: bigint) TableScan alias: src_thrift Statistics: Num rows: 11 Data size: 3070 Basic stats: COMPLETE Column stats: NONE @@ -135,18 +151,22 @@ STAGE PLANS: Statistics: Num rows: 11 Data size: 3070 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1522 Data size: 59264 Basic stats: COMPLETE Column stats: PARTIAL - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1522 Data size: 59264 Basic stats: COMPLETE Column stats: PARTIAL + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -154,13 +174,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/union22.q.out b/ql/src/test/results/clientpositive/union22.q.out index c62a90d..432faf1 100644 --- a/ql/src/test/results/clientpositive/union22.q.out +++ b/ql/src/test/results/clientpositive/union22.q.out @@ -468,68 +468,76 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 5622 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 348 Data size: 9684 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Static Partition Specification: ds=2/ + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 348 Data size: 9684 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 1 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns k1,k2,k3,k4 - columns.comments - columns.types string:string:string:string + NumFilesPerFileSink: 1 + Static Partition Specification: ds=2/ + Statistics: Num rows: 348 Data size: 9684 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### - name default.dst_union22 - partition_columns ds - partition_columns.types string - serialization.ddl struct dst_union22 { string k1, string k2, string k3, string k4} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns k1,k2,k3,k4 + columns.comments + columns.types string:string:string:string #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dst_union22 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false + name default.dst_union22 + partition_columns ds + partition_columns.types string + serialization.ddl struct dst_union22 { string k1, string k2, string k3, string k4} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dst_union22 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false TableScan GatherStats: false Union Statistics: Num rows: 348 Data size: 9684 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Static Partition Specification: ds=2/ + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 348 Data size: 9684 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 1 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns k1,k2,k3,k4 - columns.comments - columns.types string:string:string:string + NumFilesPerFileSink: 1 + Static Partition Specification: ds=2/ + Statistics: Num rows: 348 Data size: 9684 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### - name default.dst_union22 - partition_columns ds - partition_columns.types string - serialization.ddl struct dst_union22 { string k1, string k2, string k3, string k4} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns k1,k2,k3,k4 + columns.comments + columns.types string:string:string:string #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dst_union22 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false + name default.dst_union22 + partition_columns ds + partition_columns.types string + serialization.ddl struct dst_union22 { string k1, string k2, string k3, string k4} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dst_union22 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: diff --git a/ql/src/test/results/clientpositive/union23.q.out b/ql/src/test/results/clientpositive/union23.q.out index 9773741..ca5ab25 100644 --- a/ql/src/test/results/clientpositive/union23.q.out +++ b/ql/src/test/results/clientpositive/union23.q.out @@ -40,10 +40,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -53,10 +57,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) diff --git a/ql/src/test/results/clientpositive/union25.q.out b/ql/src/test/results/clientpositive/union25.q.out index 6be39ed..578853a 100644 --- a/ql/src/test/results/clientpositive/union25.q.out +++ b/ql/src/test/results/clientpositive/union25.q.out @@ -68,16 +68,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: null-subquery2:a-subquery2:master_table-subquery1:t-subquery1:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -87,16 +87,16 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE TableScan - alias: a + alias: null-subquery2:a-subquery2:master_table-subquery2:t-subquery2:b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -109,11 +109,11 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), key (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -126,17 +126,40 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: null-subquery1:a-subquery1:a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + TableScan + Union + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -146,31 +169,16 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) - TableScan - Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: bigint), _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: $f2 (type: bigint), $f0 (type: string), $f1 (type: string) + outputColumnNames: counts, key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/union26.q.out b/ql/src/test/results/clientpositive/union26.q.out index 287a9e1..8113d1f 100644 --- a/ql/src/test/results/clientpositive/union26.q.out +++ b/ql/src/test/results/clientpositive/union26.q.out @@ -87,12 +87,16 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -100,18 +104,22 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Group By Operator + aggregations: count(1) + keys: _col0 (type: string), _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) TableScan alias: srcpart Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -130,18 +138,22 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Group By Operator + aggregations: count(1) + keys: _col0 (type: string), _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) Select Operator expressions: array(1,2,3) (type: array) outputColumnNames: _col0 @@ -158,18 +170,22 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Group By Operator + aggregations: count(1) + keys: _col0 (type: string), _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) diff --git a/ql/src/test/results/clientpositive/union28.q.out b/ql/src/test/results/clientpositive/union28.q.out index 38f8ee6..1748b5d 100644 --- a/ql/src/test/results/clientpositive/union28.q.out +++ b/ql/src/test/results/clientpositive/union28.q.out @@ -49,14 +49,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery2:a-subquery2-subquery1:subq-subquery1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -69,29 +69,33 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1:a-subquery1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -106,7 +110,7 @@ STAGE PLANS: Union Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -121,7 +125,7 @@ STAGE PLANS: Union Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -189,14 +193,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery2:a-subquery2-subquery2:subq-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -209,14 +213,18 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe PREHOOK: query: insert overwrite table union_subq_union select * from ( @@ -246,8 +254,8 @@ select * from ( POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@union_subq_union -POSTHOOK: Lineage: union_subq_union.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: union_subq_union.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: union_subq_union.key EXPRESSION [(src)null-subquery1:a-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:a-subquery2-subquery1:subq-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:a-subquery2-subquery2:subq-subquery2:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: union_subq_union.value EXPRESSION [(src)null-subquery1:a-subquery1:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery2:a-subquery2-subquery1:subq-subquery1:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery2:a-subquery2-subquery2:subq-subquery2:src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from union_subq_union order by key, value limit 20 PREHOOK: type: QUERY PREHOOK: Input: default@union_subq_union diff --git a/ql/src/test/results/clientpositive/union29.q.out b/ql/src/test/results/clientpositive/union29.q.out index 87ba275..d12dc64 100644 --- a/ql/src/test/results/clientpositive/union29.q.out +++ b/ql/src/test/results/clientpositive/union29.q.out @@ -47,16 +47,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1:a-subquery1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -68,16 +68,16 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.union_subq_union TableScan - alias: src + alias: null-subquery2:a-subquery2-subquery1:subq-subquery1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -89,16 +89,16 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.union_subq_union TableScan - alias: src + alias: null-subquery2:a-subquery2-subquery2:subq-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -190,8 +190,8 @@ select * from ( POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@union_subq_union -POSTHOOK: Lineage: union_subq_union.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: union_subq_union.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: union_subq_union.key EXPRESSION [(src)null-subquery1:a-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:a-subquery2-subquery1:subq-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:a-subquery2-subquery2:subq-subquery2:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: union_subq_union.value EXPRESSION [(src)null-subquery1:a-subquery1:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery2:a-subquery2-subquery1:subq-subquery1:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery2:a-subquery2-subquery2:subq-subquery2:src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from union_subq_union order by key, value limit 20 PREHOOK: type: QUERY PREHOOK: Input: default@union_subq_union diff --git a/ql/src/test/results/clientpositive/union3.q.out b/ql/src/test/results/clientpositive/union3.q.out index 1cb211c..cb502c0 100644 --- a/ql/src/test/results/clientpositive/union3.q.out +++ b/ql/src/test/results/clientpositive/union3.q.out @@ -60,19 +60,21 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Operator Tree: - Limit - Number of rows: 1 + Select Operator Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator - expressions: 1 (type: int) - outputColumnNames: _col0 + Limit + Number of rows: 1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -80,35 +82,51 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE TableScan Union Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE TableScan Union Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE TableScan Union Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int) @@ -137,19 +155,21 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Operator Tree: - Limit - Number of rows: 1 + Select Operator Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator - expressions: 2 (type: int) - outputColumnNames: _col0 + Limit + Number of rows: 1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: 2 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -166,19 +186,21 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Operator Tree: - Limit - Number of rows: 1 + Select Operator Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator - expressions: 3 (type: int) - outputColumnNames: _col0 + Limit + Number of rows: 1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: 3 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-5 Map Reduce @@ -195,19 +217,21 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Operator Tree: - Limit - Number of rows: 1 + Select Operator Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator - expressions: 4 (type: int) - outputColumnNames: _col0 + Limit + Number of rows: 1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: 4 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/union30.q.out b/ql/src/test/results/clientpositive/union30.q.out index 894ed49..a8786e5 100644 --- a/ql/src/test/results/clientpositive/union30.q.out +++ b/ql/src/test/results/clientpositive/union30.q.out @@ -63,14 +63,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1:aa-subquery1-subquery2:a-subquery2-subquery1:subq-subquery1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -83,29 +83,33 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1:aa-subquery1-subquery1:a-subquery1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -120,7 +124,7 @@ STAGE PLANS: Union Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -135,7 +139,7 @@ STAGE PLANS: Union Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -147,16 +151,16 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.union_subq_union TableScan - alias: src + alias: null-subquery2:aa-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -224,14 +228,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1:aa-subquery1-subquery2:a-subquery2-subquery2:subq-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -244,14 +248,18 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe PREHOOK: query: insert overwrite table union_subq_union select * from ( @@ -295,8 +303,8 @@ select key, value from src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@union_subq_union -POSTHOOK: Lineage: union_subq_union.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: union_subq_union.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: union_subq_union.key EXPRESSION [(src)null-subquery1:aa-subquery1-subquery1:a-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1:aa-subquery1-subquery2:a-subquery2-subquery1:subq-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1:aa-subquery1-subquery2:a-subquery2-subquery2:subq-subquery2:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:aa-subquery2:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: union_subq_union.value EXPRESSION [(src)null-subquery1:aa-subquery1-subquery1:a-subquery1:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery1:aa-subquery1-subquery2:a-subquery2-subquery1:subq-subquery1:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery1:aa-subquery1-subquery2:a-subquery2-subquery2:subq-subquery2:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery2:aa-subquery2:src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from union_subq_union order by key, value limit 20 PREHOOK: type: QUERY PREHOOK: Input: default@union_subq_union diff --git a/ql/src/test/results/clientpositive/union32.q.out b/ql/src/test/results/clientpositive/union32.q.out index 22b7bbc..9dfeaa5 100644 --- a/ql/src/test/results/clientpositive/union32.q.out +++ b/ql/src/test/results/clientpositive/union32.q.out @@ -53,35 +53,43 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: null-subquery1:a-subquery1:t1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(key) (type: double) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: double) - sort order: + + Select Operator + expressions: key (type: double) + outputColumnNames: key Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: double) + sort order: + + Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE TableScan - alias: t2 + alias: null-subquery2:a-subquery2:t2 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(UDFToLong(key)) (type: double) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: double) - sort order: + + Select Operator + expressions: key (type: double) + outputColumnNames: key Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: double) + sort order: + + Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: double) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -204,13 +212,17 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: double) + outputColumnNames: _col0 Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: t2 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -220,13 +232,17 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: double) + outputColumnNames: _col0 Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -359,6 +375,24 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TableScan + Union + Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE @@ -366,16 +400,6 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - Union - Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -502,13 +526,17 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: double), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: t2 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -518,13 +546,17 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: double), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -657,6 +689,24 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: double), _col1 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TableScan + Union + Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: double), _col1 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE @@ -664,16 +714,6 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - Union - Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 15 Data size: 108 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/union33.q.out b/ql/src/test/results/clientpositive/union33.q.out index 308cd8b..ee671a4 100644 --- a/ql/src/test/results/clientpositive/union33.q.out +++ b/ql/src/test/results/clientpositive/union33.q.out @@ -49,15 +49,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery2:a-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -96,11 +96,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToString(_col1) (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), UDFToString($f1) (type: string) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -113,36 +113,44 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1:a-subquery1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 0.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '0' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: '0.0' (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_src + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.test_src TableScan Union Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_src + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.test_src Stage: Stage-8 Conditional Operator @@ -218,8 +226,8 @@ UNION ALL POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_src -POSTHOOK: Lineage: test_src.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_src.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), (src)src.null, ] +POSTHOOK: Lineage: test_src.key EXPRESSION [(src)null-subquery1:a-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:a-subquery2:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: test_src.value EXPRESSION [(src)null-subquery1:a-subquery1:src.FieldSchema(name:value, type:string, comment:default), (src)null-subquery2:a-subquery2:src.null, ] PREHOOK: query: SELECT COUNT(*) FROM test_src PREHOOK: type: QUERY PREHOOK: Input: default@test_src @@ -264,15 +272,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1:a-subquery1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -311,11 +319,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: final - outputColumnNames: _col0, _col1 + outputColumnNames: key, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToString(_col1) (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), UDFToString($f1) (type: string) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -330,34 +338,42 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_src + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.test_src TableScan - alias: src + alias: null-subquery2:a-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 0.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '0' (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_src + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.test_src Stage: Stage-9 Conditional Operator @@ -433,8 +449,8 @@ UNION ALL POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_src -POSTHOOK: Lineage: test_src.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_src.value EXPRESSION [(src)src.null, (src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: test_src.key EXPRESSION [(src)null-subquery1:a-subquery1:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:a-subquery2:src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: test_src.value EXPRESSION [(src)null-subquery1:a-subquery1:src.null, (src)null-subquery2:a-subquery2:src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT COUNT(*) FROM test_src PREHOOK: type: QUERY PREHOOK: Input: default@test_src diff --git a/ql/src/test/results/clientpositive/union34.q.out b/ql/src/test/results/clientpositive/union34.q.out index 9ee382b..d6842b3 100644 --- a/ql/src/test/results/clientpositive/union34.q.out +++ b/ql/src/test/results/clientpositive/union34.q.out @@ -119,11 +119,15 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) TableScan alias: src10_4 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE @@ -133,11 +137,15 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) TableScan alias: src10_2 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE @@ -156,13 +164,21 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Union Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -307,12 +323,16 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -320,11 +340,15 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) TableScan alias: src10_3 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE @@ -334,11 +358,15 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) TableScan alias: src10_4 Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE @@ -348,11 +376,15 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 25 Data size: 265 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) diff --git a/ql/src/test/results/clientpositive/union4.q.out b/ql/src/test/results/clientpositive/union4.q.out index 41ca811..d9c6aac 100644 --- a/ql/src/test/results/clientpositive/union4.q.out +++ b/ql/src/test/results/clientpositive/union4.q.out @@ -45,12 +45,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1:unionsrc-subquery1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -62,11 +64,11 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst1' (type: string), _col0 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: 'tst1' (type: string), $f0 (type: bigint) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -82,7 +84,7 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + expressions: key (type: char(4)), UDFToInteger(value) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -97,7 +99,7 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + expressions: key (type: char(4)), UDFToInteger(value) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -165,12 +167,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery2:unionsrc-subquery2:s2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -182,11 +186,11 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst2' (type: string), _col0 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: 'tst2' (type: string), $f0 (type: bigint) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/union5.q.out b/ql/src/test/results/clientpositive/union5.q.out index 75389f8..76150b5 100644 --- a/ql/src/test/results/clientpositive/union5.q.out +++ b/ql/src/test/results/clientpositive/union5.q.out @@ -25,29 +25,24 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1:unionsrc-subquery1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator expressions: 'tst1' (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: key + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE File Output Operator compressed: false table: @@ -60,76 +55,83 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator + expressions: key (type: char(4)), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: char(4)) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: char(4)) + sort order: + + Map-reduce partition columns: _col0 (type: char(4)) + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 2 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator + expressions: key (type: char(4)), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator + aggregations: count($f1) + keys: $f0 (type: char(4)) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: char(4)) + sort order: + + Map-reduce partition columns: _col0 (type: char(4)) + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) + keys: KEY._col0 (type: char(4)) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: $f0 (type: char(4)), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery2:unionsrc-subquery2:s2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator expressions: 'tst2' (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: key + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/union6.q.out b/ql/src/test/results/clientpositive/union6.q.out index 0844165..4ca1beb 100644 --- a/ql/src/test/results/clientpositive/union6.q.out +++ b/ql/src/test/results/clientpositive/union6.q.out @@ -42,12 +42,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1:unionsrc-subquery1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -59,11 +61,11 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: 'tst1' (type: string), UDFToString(_col0) (type: string) - outputColumnNames: _col0, _col1 + expressions: 'tst1' (type: string), UDFToString($f0) (type: string) + outputColumnNames: key, value Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -78,31 +80,39 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 26 Data size: 463 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false - Statistics: Num rows: 26 Data size: 463 Basic stats: COMPLETE Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmptable - TableScan - alias: s2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 26 Data size: 463 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 463 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.tmptable + TableScan + alias: null-subquery2:unionsrc-subquery2:s2 + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 26 Data size: 463 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: PARTIAL + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmptable Stage: Stage-8 Conditional Operator @@ -172,8 +182,8 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@tmptable -POSTHOOK: Lineage: tmptable.key EXPRESSION [(src1)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmptable.value EXPRESSION [(src1)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: tmptable.key EXPRESSION [(src1)null-subquery2:unionsrc-subquery2:s2.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: tmptable.value EXPRESSION [(src1)null-subquery2:unionsrc-subquery2:s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from tmptable x sort by x.key, x.value PREHOOK: type: QUERY PREHOOK: Input: default@tmptable diff --git a/ql/src/test/results/clientpositive/union7.q.out b/ql/src/test/results/clientpositive/union7.q.out index 592f073..2a80e13 100644 --- a/ql/src/test/results/clientpositive/union7.q.out +++ b/ql/src/test/results/clientpositive/union7.q.out @@ -24,29 +24,24 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1:unionsrc-subquery1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator expressions: 'tst1' (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: key + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE File Output Operator compressed: false table: @@ -59,54 +54,66 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: PARTIAL - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col1 (type: bigint) - TableScan - alias: s2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 26 Data size: 279 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 191 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: bigint) + TableScan + alias: null-subquery2:unionsrc-subquery2:s2 + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 26 Data size: 191 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: PARTIAL + Group By Operator + aggregations: count($f1) + keys: $f0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/union8.q.out b/ql/src/test/results/clientpositive/union8.q.out index a4d6477..416431b 100644 --- a/ql/src/test/results/clientpositive/union8.q.out +++ b/ql/src/test/results/clientpositive/union8.q.out @@ -23,53 +23,65 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1-subquery1:unionsrc-subquery1-subquery1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: s1 + alias: null-subquery1-subquery2:unionsrc-subquery1-subquery2:s2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: s1 + alias: null-subquery2:unionsrc-subquery2:s3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/union9.q.out b/ql/src/test/results/clientpositive/union9.q.out index ec7ab35..1391e52 100644 --- a/ql/src/test/results/clientpositive/union9.q.out +++ b/ql/src/test/results/clientpositive/union9.q.out @@ -23,18 +23,20 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1-subquery1:unionsrc-subquery1-subquery1:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -43,18 +45,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: s1 + alias: null-subquery1-subquery2:unionsrc-subquery1-subquery2:s2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -63,18 +67,20 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: s1 + alias: null-subquery2:unionsrc-subquery2:s3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -86,15 +92,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/union_date_trim.q.out b/ql/src/test/results/clientpositive/union_date_trim.q.out index e2f5269..65e7a8e 100644 --- a/ql/src/test/results/clientpositive/union_date_trim.q.out +++ b/ql/src/test/results/clientpositive/union_date_trim.q.out @@ -50,5 +50,5 @@ insert into table testDate select id, tm from (select id, dt as tm from testDate POSTHOOK: type: QUERY POSTHOOK: Input: default@testdate POSTHOOK: Output: default@testdate -POSTHOOK: Lineage: testdate.dt EXPRESSION [(testdate)testdate.FieldSchema(name:dt, type:date, comment:null), ] -POSTHOOK: Lineage: testdate.id EXPRESSION [(testdate)testdate.FieldSchema(name:id, type:int, comment:null), ] +POSTHOOK: Lineage: testdate.dt EXPRESSION [(testdate)null-subquery1-subquery1:a-subquery1-subquery1:testdate.FieldSchema(name:dt, type:date, comment:null), (testdate)null-subquery1-subquery2:a-subquery1-subquery2:testdate.FieldSchema(name:dt, type:date, comment:null), (testdate)null-subquery2:a-subquery2:testdate.FieldSchema(name:dt, type:date, comment:null), ] +POSTHOOK: Lineage: testdate.id EXPRESSION [(testdate)null-subquery1-subquery1:a-subquery1-subquery1:testdate.FieldSchema(name:id, type:int, comment:null), (testdate)null-subquery1-subquery2:a-subquery1-subquery2:testdate.FieldSchema(name:id, type:int, comment:null), (testdate)null-subquery2:a-subquery2:testdate.FieldSchema(name:id, type:int, comment:null), ] diff --git a/ql/src/test/results/clientpositive/union_null.q.out b/ql/src/test/results/clientpositive/union_null.q.out index 32cdf65..77afe2e 100644 --- a/ql/src/test/results/clientpositive/union_null.q.out +++ b/ql/src/test/results/clientpositive/union_null.q.out @@ -12,11 +12,6 @@ select x from (select * from (select value as x from src order by x limit 5)a un POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -val_0 -val_0 -val_0 -val_10 -val_100 NULL NULL NULL diff --git a/ql/src/test/results/clientpositive/union_remove_1.q.out b/ql/src/test/results/clientpositive/union_remove_1.q.out index 35e4458..472c761 100644 --- a/ql/src/test/results/clientpositive/union_remove_1.q.out +++ b/ql/src/test/results/clientpositive/union_remove_1.q.out @@ -70,15 +70,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1:a-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -93,16 +93,20 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 Stage: Stage-0 Move Operator @@ -118,15 +122,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -141,16 +145,20 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 PREHOOK: query: insert overwrite table outputTbl1 SELECT * @@ -172,8 +180,8 @@ FROM ( POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE PREHOOK: Input: default@outputtbl1 diff --git a/ql/src/test/results/clientpositive/union_remove_10.q.out b/ql/src/test/results/clientpositive/union_remove_10.q.out index 2159b7e..5540030 100644 --- a/ql/src/test/results/clientpositive/union_remove_10.q.out +++ b/ql/src/test/results/clientpositive/union_remove_10.q.out @@ -92,11 +92,11 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1:b-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1 (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: key, values Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -150,15 +150,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:b-subquery2-subquery1:a-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -173,26 +173,30 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: key, values Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat - serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.outputtbl1 Stage: Stage-8 Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:b-subquery2-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2 (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: key, values Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -231,8 +235,8 @@ select * FROM ( POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)null-subquery1:b-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:b-subquery2-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:b-subquery2-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)null-subquery2:b-subquery2-subquery1:a-subquery1:inputtbl1.null, ] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE PREHOOK: Input: default@outputtbl1 diff --git a/ql/src/test/results/clientpositive/union_remove_11.q.out b/ql/src/test/results/clientpositive/union_remove_11.q.out index 2ab83dc..c56d988 100644 --- a/ql/src/test/results/clientpositive/union_remove_11.q.out +++ b/ql/src/test/results/clientpositive/union_remove_11.q.out @@ -90,16 +90,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1:b-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1 (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, values Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint) + expressions: key (type: string), UDFToLong(values) (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -111,16 +111,16 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe name: default.outputtbl1 TableScan - alias: inputtbl1 + alias: null-subquery2:b-subquery2-subquery1:a-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2 (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, values Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint) + expressions: key (type: string), UDFToLong(values) (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -132,16 +132,16 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe name: default.outputtbl1 TableScan - alias: inputtbl1 + alias: null-subquery2:b-subquery2-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 3 (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, values Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint) + expressions: key (type: string), UDFToLong(values) (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -220,7 +220,7 @@ select * FROM ( POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)null-subquery1:b-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:b-subquery2-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:b-subquery2-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl1.values EXPRESSION [] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE diff --git a/ql/src/test/results/clientpositive/union_remove_15.q.out b/ql/src/test/results/clientpositive/union_remove_15.q.out index a259df8..88ffa70 100644 --- a/ql/src/test/results/clientpositive/union_remove_15.q.out +++ b/ql/src/test/results/clientpositive/union_remove_15.q.out @@ -76,15 +76,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1:a-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -99,11 +99,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), '1' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f1 (type: bigint), '1' (type: string) + outputColumnNames: key, values, ds Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -130,15 +130,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -153,11 +153,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), '2' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f1 (type: bigint), '2' (type: string) + outputColumnNames: key, values, ds Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -189,10 +189,10 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1@ds=1 POSTHOOK: Output: default@outputtbl1@ds=2 -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=1).key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=1).values EXPRESSION [(inputtbl1)inputtbl1.null, ] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=2).key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=2).values EXPRESSION [(inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=1).key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=1).values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=2).key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=2).values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE PREHOOK: Input: default@outputtbl1 diff --git a/ql/src/test/results/clientpositive/union_remove_16.q.out b/ql/src/test/results/clientpositive/union_remove_16.q.out index c7a08f3..1b7c519 100644 --- a/ql/src/test/results/clientpositive/union_remove_16.q.out +++ b/ql/src/test/results/clientpositive/union_remove_16.q.out @@ -79,15 +79,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1:a-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -102,11 +102,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), '1' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f1 (type: bigint), '1' (type: string) + outputColumnNames: key, values, ds Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -162,15 +162,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -185,11 +185,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), '2' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f1 (type: bigint), '2' (type: string) + outputColumnNames: key, values, ds Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -221,10 +221,10 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1@ds=1 POSTHOOK: Output: default@outputtbl1@ds=2 -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=1).key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=1).values EXPRESSION [(inputtbl1)inputtbl1.null, ] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=2).key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=2).values EXPRESSION [(inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=1).key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=1).values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=2).key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=2).values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE PREHOOK: Input: default@outputtbl1 diff --git a/ql/src/test/results/clientpositive/union_remove_17.q.out b/ql/src/test/results/clientpositive/union_remove_17.q.out index 688e365..39fc807 100644 --- a/ql/src/test/results/clientpositive/union_remove_17.q.out +++ b/ql/src/test/results/clientpositive/union_remove_17.q.out @@ -69,16 +69,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1:a-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1 (type: int), '1' (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, values, ds Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint), _col2 (type: string) + expressions: key (type: string), UDFToLong(values) (type: bigint), ds (type: char(1)) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -90,16 +90,16 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe name: default.outputtbl1 TableScan - alias: inputtbl1 + alias: null-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2 (type: int), '2' (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, values, ds Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint), _col2 (type: string) + expressions: key (type: string), UDFToLong(values) (type: bigint), ds (type: char(1)) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -144,9 +144,9 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1@ds=1 POSTHOOK: Output: default@outputtbl1@ds=2 -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=1).key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=1).key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl1 PARTITION(ds=1).values EXPRESSION [] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=2).key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=2).key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl1 PARTITION(ds=2).values EXPRESSION [] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE diff --git a/ql/src/test/results/clientpositive/union_remove_18.q.out b/ql/src/test/results/clientpositive/union_remove_18.q.out index 96daa12..31eb289 100644 --- a/ql/src/test/results/clientpositive/union_remove_18.q.out +++ b/ql/src/test/results/clientpositive/union_remove_18.q.out @@ -74,15 +74,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1:a-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), ds (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), ds (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -97,11 +97,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: bigint), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f2 (type: bigint), $f1 (type: string) + outputColumnNames: key, values, ds Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -128,15 +128,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), ds (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), ds (type: string), 1 (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count($f2) + keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -151,11 +151,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: bigint), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: $f0 (type: string), $f2 (type: bigint), $f1 (type: string) + outputColumnNames: key, values, ds Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -191,18 +191,18 @@ POSTHOOK: Output: default@outputtbl1@ds=13 POSTHOOK: Output: default@outputtbl1@ds=17 POSTHOOK: Output: default@outputtbl1@ds=18 POSTHOOK: Output: default@outputtbl1@ds=28 -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=11).key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=11).values EXPRESSION [(inputtbl1)inputtbl1.null, ] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=12).key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=12).values EXPRESSION [(inputtbl1)inputtbl1.null, ] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=13).key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=13).values EXPRESSION [(inputtbl1)inputtbl1.null, ] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=17).key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=17).values EXPRESSION [(inputtbl1)inputtbl1.null, ] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=18).key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=18).values EXPRESSION [(inputtbl1)inputtbl1.null, ] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=28).key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=28).values EXPRESSION [(inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=11).key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=11).values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=12).key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=12).values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=13).key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=13).values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=17).key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=17).values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=18).key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=18).values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=28).key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=28).values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE PREHOOK: Input: default@outputtbl1 diff --git a/ql/src/test/results/clientpositive/union_remove_19.q.out b/ql/src/test/results/clientpositive/union_remove_19.q.out index c1f688e..54cea65 100644 --- a/ql/src/test/results/clientpositive/union_remove_19.q.out +++ b/ql/src/test/results/clientpositive/union_remove_19.q.out @@ -74,15 +74,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1:a-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -97,16 +97,20 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 Stage: Stage-0 Move Operator @@ -122,15 +126,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -145,16 +149,20 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 PREHOOK: query: insert overwrite table outputTbl1 SELECT a.key, a.`values` @@ -176,8 +184,8 @@ FROM ( POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE PREHOOK: Input: default@outputtbl1 @@ -261,18 +269,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1:a-subquery1:inputtbl1 Statistics: Num rows: 10 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 7.0) (type: boolean) Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '7' (type: string) - outputColumnNames: _col0 + expressions: '7' (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE @@ -287,16 +295,20 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 Stage: Stage-0 Move Operator @@ -312,18 +324,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 10 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 7.0) (type: boolean) Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '7' (type: string) - outputColumnNames: _col0 + expressions: '7' (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE @@ -338,16 +350,20 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 PREHOOK: query: insert overwrite table outputTbl1 SELECT a.key, a.`values` @@ -369,8 +385,8 @@ FROM ( POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] PREHOOK: query: select * from outputTbl1 PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl1 @@ -417,18 +433,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: b-subquery1:a-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) + UDFToDouble(key)) >= 7.0) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -443,11 +459,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (UDFToDouble(_col0) + UDFToDouble(_col0)) (type: double), _col1 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: (UDFToDouble($f0) + UDFToDouble($f0)) (type: double), $f1 (type: bigint) + outputColumnNames: key, values Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -472,18 +488,18 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: b-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) + UDFToDouble(key)) >= 7.0) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -498,11 +514,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (UDFToDouble(_col0) + UDFToDouble(_col0)) (type: double), _col1 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: (UDFToDouble($f0) + UDFToDouble($f0)) (type: double), $f1 (type: bigint) + outputColumnNames: key, values Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -539,8 +555,8 @@ FROM ( POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)b-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)b-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)b-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)b-subquery2:a-subquery2:inputtbl1.null, ] PREHOOK: query: select * from outputTbl1 order by key, `values` PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl1 diff --git a/ql/src/test/results/clientpositive/union_remove_2.q.out b/ql/src/test/results/clientpositive/union_remove_2.q.out index 29e5d6c..f0a9fbe 100644 --- a/ql/src/test/results/clientpositive/union_remove_2.q.out +++ b/ql/src/test/results/clientpositive/union_remove_2.q.out @@ -77,15 +77,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1-subquery1:a-subquery1-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -100,16 +100,20 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 Stage: Stage-0 Move Operator @@ -125,11 +129,11 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1-subquery2:a-subquery1-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1 (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -144,11 +148,11 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2 (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -183,8 +187,8 @@ FROM ( POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)null-subquery1-subquery1:a-subquery1-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery1-subquery2:a-subquery1-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)null-subquery1-subquery1:a-subquery1-subquery1:inputtbl1.null, ] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE PREHOOK: Input: default@outputtbl1 diff --git a/ql/src/test/results/clientpositive/union_remove_20.q.out b/ql/src/test/results/clientpositive/union_remove_20.q.out index 1da81a7..91f050c 100644 --- a/ql/src/test/results/clientpositive/union_remove_20.q.out +++ b/ql/src/test/results/clientpositive/union_remove_20.q.out @@ -72,15 +72,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1:a-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -95,11 +95,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint), _col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: $f1 (type: bigint), $f0 (type: string) + outputColumnNames: values, key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -124,15 +124,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -147,11 +147,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint), _col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: $f1 (type: bigint), $f0 (type: string) + outputColumnNames: values, key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -182,8 +182,8 @@ FROM ( POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE PREHOOK: Input: default@outputtbl1 diff --git a/ql/src/test/results/clientpositive/union_remove_21.q.out b/ql/src/test/results/clientpositive/union_remove_21.q.out index 4743d8d..4092c09 100644 --- a/ql/src/test/results/clientpositive/union_remove_21.q.out +++ b/ql/src/test/results/clientpositive/union_remove_21.q.out @@ -72,14 +72,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1:a-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -92,16 +92,20 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 Stage: Stage-0 Move Operator @@ -117,14 +121,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -137,16 +141,20 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string) + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 PREHOOK: query: insert overwrite table outputTbl1 SELECT a.key @@ -168,7 +176,7 @@ FROM ( POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE PREHOOK: Input: default@outputtbl1 diff --git a/ql/src/test/results/clientpositive/union_remove_22.q.out b/ql/src/test/results/clientpositive/union_remove_22.q.out index 3f13991..0010aab 100644 --- a/ql/src/test/results/clientpositive/union_remove_22.q.out +++ b/ql/src/test/results/clientpositive/union_remove_22.q.out @@ -269,15 +269,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1:a-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -292,10 +292,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToLong(concat(_col1, _col1)) (type: bigint), UDFToLong(concat(_col1, _col1)) (type: bigint) + expressions: $f0 (type: string), UDFToLong(concat($f1, $f1)) (type: bigint), UDFToLong(concat($f1, $f1)) (type: bigint) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -321,15 +321,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -344,10 +344,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToLong(concat(_col1, _col1)) (type: bigint), UDFToLong(concat(_col1, _col1)) (type: bigint) + expressions: $f0 (type: string), UDFToLong(concat($f1, $f1)) (type: bigint), UDFToLong(concat($f1, $f1)) (type: bigint) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -379,9 +379,9 @@ FROM ( POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, ] -POSTHOOK: Lineage: outputtbl1.values2 EXPRESSION [(inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1.values2 EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] PREHOOK: query: select * from outputTbl1 order by key, `values` PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl1 diff --git a/ql/src/test/results/clientpositive/union_remove_23.q.out b/ql/src/test/results/clientpositive/union_remove_23.q.out index cdbe914..1d32012 100644 --- a/ql/src/test/results/clientpositive/union_remove_23.q.out +++ b/ql/src/test/results/clientpositive/union_remove_23.q.out @@ -105,18 +105,22 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -135,14 +139,18 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 Stage: Stage-0 Move Operator @@ -183,14 +191,18 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 PREHOOK: query: insert overwrite table outputTbl1 SELECT * diff --git a/ql/src/test/results/clientpositive/union_remove_24.q.out b/ql/src/test/results/clientpositive/union_remove_24.q.out index 49086e4..2e9551d 100644 --- a/ql/src/test/results/clientpositive/union_remove_24.q.out +++ b/ql/src/test/results/clientpositive/union_remove_24.q.out @@ -68,15 +68,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1:a-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -91,11 +91,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToDouble(_col0) (type: double), _col1 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: UDFToDouble($f0) (type: double), $f1 (type: bigint) + outputColumnNames: key, values Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -120,15 +120,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -143,11 +143,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToDouble(UDFToLong(_col0)) (type: double), _col1 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: UDFToDouble(UDFToLong($f0)) (type: double), $f1 (type: bigint) + outputColumnNames: key, values Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -178,8 +178,8 @@ SELECT * FROM POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE PREHOOK: Input: default@outputtbl1 diff --git a/ql/src/test/results/clientpositive/union_remove_25.q.out b/ql/src/test/results/clientpositive/union_remove_25.q.out index 37d6a53..a6b906b 100644 --- a/ql/src/test/results/clientpositive/union_remove_25.q.out +++ b/ql/src/test/results/clientpositive/union_remove_25.q.out @@ -86,15 +86,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1:a-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -109,16 +109,20 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 Stage: Stage-0 Move Operator @@ -136,15 +140,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -159,16 +163,20 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 PREHOOK: query: insert overwrite table outputTbl1 partition(ds='2004') SELECT * @@ -190,8 +198,8 @@ FROM ( POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1@ds=2004 -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=2004).key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1 PARTITION(ds=2004).values EXPRESSION [(inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=2004).key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1 PARTITION(ds=2004).values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] PREHOOK: query: desc formatted outputTbl1 partition(ds='2004') PREHOOK: type: DESCTABLE PREHOOK: Input: default@outputtbl1 @@ -271,47 +279,64 @@ FROM ( POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1, Stage-2 - Stage-2 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: srcpart + alias: null-subquery1:a-subquery1:a:srcpart Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string), '2008-04-08' (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 500 Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 500 - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), UDFToLong(value) (type: bigint), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl2 + TableScan + alias: null-subquery2:a-subquery2:b:srcpart + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint), '2008-04-08' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + expressions: key (type: string), value (type: string), '2008-04-08' (type: string) + outputColumnNames: key, value, ds + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 500 Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl2 + Select Operator + expressions: key (type: string), value (type: string), ds (type: string) + outputColumnNames: key, value, ds + Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), UDFToLong(value) (type: bigint), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl2 Stage: Stage-0 Move Operator @@ -325,44 +350,6 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.outputtbl2 - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 500 - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 500 - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint), '2008-04-08' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl2 - PREHOOK: query: insert overwrite table outputTbl2 partition(ds) SELECT * FROM ( @@ -387,8 +374,8 @@ POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 POSTHOOK: Output: default@outputtbl2@ds=2008-04-08 -POSTHOOK: Lineage: outputtbl2 PARTITION(ds=2008-04-08).key EXPRESSION [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: outputtbl2 PARTITION(ds=2008-04-08).values EXPRESSION [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: outputtbl2 PARTITION(ds=2008-04-08).key EXPRESSION [(srcpart)null-subquery1:a-subquery1:a:srcpart.FieldSchema(name:key, type:string, comment:default), (srcpart)null-subquery2:a-subquery2:b:srcpart.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: outputtbl2 PARTITION(ds=2008-04-08).values EXPRESSION [(srcpart)null-subquery1:a-subquery1:a:srcpart.FieldSchema(name:value, type:string, comment:default), (srcpart)null-subquery2:a-subquery2:b:srcpart.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: show partitions outputTbl2 PREHOOK: type: SHOWPARTITIONS PREHOOK: Input: default@outputtbl2 @@ -422,7 +409,7 @@ Partition Parameters: numFiles 2 numRows -1 rawDataSize -1 - totalSize 6812 + totalSize 13624 #### A masked pattern was here #### # Storage Information @@ -453,47 +440,64 @@ FROM ( POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1, Stage-2 - Stage-2 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: srcpart + alias: null-subquery1:a-subquery1:a:srcpart Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col3 + expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) + outputColumnNames: key, value, ds, hr Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1000 Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col3 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 1000 - Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 2000 Data size: 20000 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), UDFToLong(value) (type: bigint), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 20000 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2000 Data size: 20000 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl3 + TableScan + alias: null-subquery2:a-subquery2:b:srcpart + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint), '2008-04-08' (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 1000 Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl3 + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 2000 Data size: 20000 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), UDFToLong(value) (type: bigint), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 20000 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2000 Data size: 20000 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl3 Stage: Stage-0 Move Operator @@ -508,44 +512,6 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.outputtbl3 - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 1000 - Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col3 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 1000 - Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint), '2008-04-08' (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1000 Data size: 10000 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl3 - PREHOOK: query: insert overwrite table outputTbl3 partition(ds, hr) SELECT * FROM ( @@ -571,10 +537,10 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 POSTHOOK: Output: default@outputtbl3@ds=2008-04-08/hr=11 POSTHOOK: Output: default@outputtbl3@ds=2008-04-08/hr=12 -POSTHOOK: Lineage: outputtbl3 PARTITION(ds=2008-04-08,hr=11).key EXPRESSION [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: outputtbl3 PARTITION(ds=2008-04-08,hr=11).values EXPRESSION [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: outputtbl3 PARTITION(ds=2008-04-08,hr=12).key EXPRESSION [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: outputtbl3 PARTITION(ds=2008-04-08,hr=12).values EXPRESSION [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: outputtbl3 PARTITION(ds=2008-04-08,hr=11).key EXPRESSION [(srcpart)null-subquery1:a-subquery1:a:srcpart.FieldSchema(name:key, type:string, comment:default), (srcpart)null-subquery2:a-subquery2:b:srcpart.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: outputtbl3 PARTITION(ds=2008-04-08,hr=11).values EXPRESSION [(srcpart)null-subquery1:a-subquery1:a:srcpart.FieldSchema(name:value, type:string, comment:default), (srcpart)null-subquery2:a-subquery2:b:srcpart.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: outputtbl3 PARTITION(ds=2008-04-08,hr=12).key EXPRESSION [(srcpart)null-subquery1:a-subquery1:a:srcpart.FieldSchema(name:key, type:string, comment:default), (srcpart)null-subquery2:a-subquery2:b:srcpart.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: outputtbl3 PARTITION(ds=2008-04-08,hr=12).values EXPRESSION [(srcpart)null-subquery1:a-subquery1:a:srcpart.FieldSchema(name:value, type:string, comment:default), (srcpart)null-subquery2:a-subquery2:b:srcpart.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: show partitions outputTbl3 PREHOOK: type: SHOWPARTITIONS PREHOOK: Input: default@outputtbl3 @@ -607,7 +573,7 @@ Table: outputtbl3 #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE false - numFiles 2 + numFiles 1 numRows -1 rawDataSize -1 totalSize 6812 diff --git a/ql/src/test/results/clientpositive/union_remove_3.q.out b/ql/src/test/results/clientpositive/union_remove_3.q.out index 7045a26..5ea7668 100644 --- a/ql/src/test/results/clientpositive/union_remove_3.q.out +++ b/ql/src/test/results/clientpositive/union_remove_3.q.out @@ -75,16 +75,16 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1-subquery1:a-subquery1-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1 (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, values Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint) + expressions: key (type: string), UDFToLong(values) (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -96,16 +96,16 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.outputtbl1 TableScan - alias: inputtbl1 + alias: null-subquery1-subquery2:a-subquery1-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2 (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, values Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint) + expressions: key (type: string), UDFToLong(values) (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -117,16 +117,16 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.outputtbl1 TableScan - alias: inputtbl1 + alias: null-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 3 (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, values Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint) + expressions: key (type: string), UDFToLong(values) (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -172,7 +172,7 @@ FROM ( POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)null-subquery1-subquery1:a-subquery1-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery1-subquery2:a-subquery1-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl1.values EXPRESSION [] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE diff --git a/ql/src/test/results/clientpositive/union_remove_4.q.out b/ql/src/test/results/clientpositive/union_remove_4.q.out index c545dd4..9dc82ea 100644 --- a/ql/src/test/results/clientpositive/union_remove_4.q.out +++ b/ql/src/test/results/clientpositive/union_remove_4.q.out @@ -75,15 +75,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1:a-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -98,16 +98,20 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 Stage: Stage-6 Conditional Operator @@ -162,15 +166,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -185,16 +189,20 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 PREHOOK: query: insert overwrite table outputTbl1 SELECT * @@ -216,8 +224,8 @@ FROM ( POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE PREHOOK: Input: default@outputtbl1 diff --git a/ql/src/test/results/clientpositive/union_remove_5.q.out b/ql/src/test/results/clientpositive/union_remove_5.q.out index 1308c09..b59d8d2 100644 --- a/ql/src/test/results/clientpositive/union_remove_5.q.out +++ b/ql/src/test/results/clientpositive/union_remove_5.q.out @@ -84,15 +84,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1-subquery1:a-subquery1-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -107,16 +107,20 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 Stage: Stage-6 Conditional Operator @@ -171,11 +175,11 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1-subquery2:a-subquery1-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1 (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -190,11 +194,11 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2 (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -229,8 +233,8 @@ FROM ( POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)null-subquery1-subquery1:a-subquery1-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery1-subquery2:a-subquery1-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)null-subquery1-subquery1:a-subquery1-subquery1:inputtbl1.null, ] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE PREHOOK: Input: default@outputtbl1 diff --git a/ql/src/test/results/clientpositive/union_remove_6.q.out b/ql/src/test/results/clientpositive/union_remove_6.q.out index 1b076c2..c62f24a 100644 --- a/ql/src/test/results/clientpositive/union_remove_6.q.out +++ b/ql/src/test/results/clientpositive/union_remove_6.q.out @@ -99,12 +99,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -112,41 +116,57 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 - File Output Operator - compressed: false + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl2 + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl2 TableScan Union Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 - File Output Operator - compressed: false + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl2 + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl2 Stage: Stage-0 Move Operator @@ -197,12 +217,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe PREHOOK: query: FROM ( SELECT key, count(1) as `values` from inputTbl1 group by key diff --git a/ql/src/test/results/clientpositive/union_remove_6_subq.q.out b/ql/src/test/results/clientpositive/union_remove_6_subq.q.out index 05363e4..30d6f21 100644 --- a/ql/src/test/results/clientpositive/union_remove_6_subq.q.out +++ b/ql/src/test/results/clientpositive/union_remove_6_subq.q.out @@ -107,12 +107,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -120,41 +124,65 @@ STAGE PLANS: TableScan Union Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl2 + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl2 TableScan Union Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl1 - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.outputtbl2 + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl1 + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.outputtbl2 Stage: Stage-0 Move Operator @@ -205,12 +233,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe PREHOOK: query: FROM ( select * from( @@ -305,12 +337,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1:subq-subquery1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -322,11 +356,11 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: (_col0 - 200) (type: bigint) - outputColumnNames: _col0 + expressions: ($f0 - 200) (type: bigint) + outputColumnNames: c Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -342,7 +376,7 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: avg(_col0) + aggregations: avg(c) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE @@ -354,7 +388,7 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: avg(_col0) + aggregations: avg(c) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE @@ -366,26 +400,32 @@ STAGE PLANS: Group By Operator aggregations: avg(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: double) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery2:subq-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 1 (type: int) + outputColumnNames: $f0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -397,14 +437,18 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: c + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -456,15 +500,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1:subq-subquery1:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -479,11 +523,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), (_col1 * 2) (type: bigint) - outputColumnNames: _col0, _col1 + expressions: $f0 (type: string), ($f1 * 2) (type: bigint) + outputColumnNames: key, c Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -499,7 +543,7 @@ STAGE PLANS: Union Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: bigint) + keys: key (type: string), c (type: bigint) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -512,7 +556,7 @@ STAGE PLANS: Union Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: bigint) + keys: key (type: string), c (type: bigint) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -525,53 +569,57 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: key, c Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: bigint - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col1 - partition by: _col0 - raw input shape: - window functions: - window function definition - alias: avg_window_0 - arguments: _col1 - name: avg - window function: GenericUDAFAverageEvaluatorDouble - window frame: PRECEDING(MAX)~ + Select Operator + expressions: key (type: string), c (type: bigint) + outputColumnNames: key, c Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), avg_window_0 (type: double) - outputColumnNames: _col0, _col1 + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: key: string, c: bigint + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: c + partition by: key + raw input shape: + window functions: + window function definition + alias: $win$_col_52 + arguments: c + name: avg + window function: GenericUDAFAverageEvaluatorDouble + window frame: PRECEDING(MAX)~ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: string), $win$_col_52 (type: double) + outputColumnNames: key, _o__c1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery2:subq-subquery2:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -586,14 +634,18 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: key, c + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/union_remove_7.q.out b/ql/src/test/results/clientpositive/union_remove_7.q.out index 61bef8b..205cc73 100644 --- a/ql/src/test/results/clientpositive/union_remove_7.q.out +++ b/ql/src/test/results/clientpositive/union_remove_7.q.out @@ -74,15 +74,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1:a-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -97,16 +97,20 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat - serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.outputtbl1 Stage: Stage-0 Move Operator @@ -122,15 +126,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -145,16 +149,20 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat - serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.outputtbl1 PREHOOK: query: insert overwrite table outputTbl1 SELECT * @@ -176,8 +184,8 @@ FROM ( POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)null-subquery1:a-subquery1:inputtbl1.null, (inputtbl1)null-subquery2:a-subquery2:inputtbl1.null, ] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE PREHOOK: Input: default@outputtbl1 diff --git a/ql/src/test/results/clientpositive/union_remove_8.q.out b/ql/src/test/results/clientpositive/union_remove_8.q.out index 62af170..3be8819 100644 --- a/ql/src/test/results/clientpositive/union_remove_8.q.out +++ b/ql/src/test/results/clientpositive/union_remove_8.q.out @@ -81,15 +81,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1-subquery1:a-subquery1-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -104,16 +104,20 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat - serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.outputtbl1 Stage: Stage-0 Move Operator @@ -129,11 +133,11 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1-subquery2:a-subquery1-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1 (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -148,11 +152,11 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2 (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -187,8 +191,8 @@ FROM ( POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)null-subquery1-subquery1:a-subquery1-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery1-subquery2:a-subquery1-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)null-subquery1-subquery1:a-subquery1-subquery1:inputtbl1.null, ] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE PREHOOK: Input: default@outputtbl1 diff --git a/ql/src/test/results/clientpositive/union_remove_9.q.out b/ql/src/test/results/clientpositive/union_remove_9.q.out index c0fc54d..149f4d1 100644 --- a/ql/src/test/results/clientpositive/union_remove_9.q.out +++ b/ql/src/test/results/clientpositive/union_remove_9.q.out @@ -87,15 +87,15 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery1:b-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -110,16 +110,20 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat - serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe - name: default.outputtbl1 + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.outputtbl1 Stage: Stage-6 Conditional Operator @@ -164,17 +168,17 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: inputtbl1 + alias: null-subquery2:b-subquery2-subquery1:a-subquery1:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1 (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, values Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint) - outputColumnNames: _col0, _col1 + expressions: key (type: string), UDFToLong(values) (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -185,17 +189,17 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe name: default.outputtbl1 TableScan - alias: inputtbl1 + alias: null-subquery2:b-subquery2-subquery2:a-subquery2:inputtbl1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2 (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, values Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint) - outputColumnNames: _col0, _col1 + expressions: key (type: string), UDFToLong(values) (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -234,8 +238,8 @@ select * FROM ( POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 -POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)null-subquery1:b-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:b-subquery2-subquery1:a-subquery1:inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)null-subquery2:b-subquery2-subquery2:a-subquery2:inputtbl1.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)null-subquery1:b-subquery1:inputtbl1.null, ] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE PREHOOK: Input: default@outputtbl1 diff --git a/ql/src/test/results/clientpositive/union_top_level.q.out b/ql/src/test/results/clientpositive/union_top_level.q.out index 2773ad8..2bed96f 100644 --- a/ql/src/test/results/clientpositive/union_top_level.q.out +++ b/ql/src/test/results/clientpositive/union_top_level.q.out @@ -20,166 +20,102 @@ select * from (select key, 2 as value from src where key % 3 == 2 limit 3)c POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-3, Stage-4 - Stage-3 is a root stage - Stage-4 is a root stage - Stage-0 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1-subquery1:_u1-subquery1-subquery1:a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) % 3.0) = 0.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 0 (type: int) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), 0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Union - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - Union - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - Union - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: + Union + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: src + alias: null-subquery1-subquery2:_u1-subquery1-subquery2:b:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) % 3.0) = 1.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 1 (type: int) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), 1 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: + Union + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: src + alias: null-subquery2:_u1-subquery2:c:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) % 3.0) = 2.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 2 (type: int) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), 2 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Union + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator - limit: -1 + limit: 3 Processor Tree: ListSink @@ -199,14 +135,8 @@ select * from (select key, 2 as value from src where key % 3 == 2 limit 3)c POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -165 0 238 1 -255 0 -27 0 -278 2 311 2 -409 1 -484 1 86 2 PREHOOK: query: explain select * from (select s1.key as k, s2.value as v from src s1 join src s2 on (s1.key = s2.key) limit 10)a @@ -220,59 +150,57 @@ select * from (select s1.key as k, s2.value as v from src s1 join src s2 on (s1. POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2, Stage-6 - Stage-5 is a root stage - Stage-6 depends on stages: Stage-5 - Stage-0 depends on stages: Stage-3 + Stage-2 depends on stages: Stage-1, Stage-4 + Stage-4 is a root stage + Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery1:_u1-subquery1:a:s2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: s1 + alias: null-subquery1:_u1-subquery1:a:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + expressions: key0 (type: string), value (type: string) + outputColumnNames: k, v Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -288,132 +216,98 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan Union Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: k (type: string), v (type: string) + outputColumnNames: k, v Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: k (type: string), v (type: string) + outputColumnNames: k, v Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-5 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan - alias: s1 + alias: null-subquery2:_u1-subquery2:b:s2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: s1 + alias: null-subquery2:_u1-subquery2:b:s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 + 0 key (type: string) + 1 key (type: string) + outputColumnNames: value, key0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + expressions: key0 (type: string), value (type: string) + outputColumnNames: k, v Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: k (type: string), v (type: string) + outputColumnNames: k, v + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator - limit: -1 + limit: 10 Processor Tree: ListSink @@ -438,16 +332,6 @@ POSTHOOK: Input: default@src 0 val_0 0 val_0 0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -10 val_10 10 val_10 PREHOOK: query: -- ctas explain @@ -469,99 +353,113 @@ select * from (select key, 2 as value from src where key % 3 == 2 limit 3)c POSTHOOK: type: CREATETABLE_AS_SELECT STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-9, Stage-10 - Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 - Stage-5 - Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 - Stage-11 depends on stages: Stage-0 - Stage-3 depends on stages: Stage-11 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 Stage-4 - Stage-6 - Stage-7 depends on stages: Stage-6 - Stage-9 is a root stage - Stage-10 is a root stage + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 + Stage-10 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-10 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1-subquery1:_u1-subquery1-subquery1:a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) % 3.0) = 0.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 0 (type: int) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), 0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: + Union + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.union_top TableScan - Union - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.union_top - TableScan - Union - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.union_top + alias: null-subquery1-subquery2:_u1-subquery1-subquery2:b:src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((UDFToDouble(key) % 3.0) = 1.0) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 3 + Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.union_top TableScan - Union - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.union_top + alias: null-subquery2:_u1-subquery2:c:src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((UDFToDouble(key) % 3.0) = 2.0) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 2 (type: int) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 3 + Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.union_top - Stage: Stage-8 + Stage: Stage-7 Conditional Operator - Stage: Stage-5 + Stage: Stage-4 Move Operator files: hdfs directory: true @@ -573,7 +471,7 @@ STAGE PLANS: hdfs directory: true #### A masked pattern was here #### - Stage: Stage-11 + Stage: Stage-10 Create Table Operator: Create Table columns: key string, value int @@ -582,10 +480,10 @@ STAGE PLANS: serde name: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.union_top - Stage: Stage-3 + Stage: Stage-2 Stats-Aggr Operator - Stage: Stage-4 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan @@ -597,7 +495,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.union_top - Stage: Stage-6 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan @@ -609,90 +507,12 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.union_top - Stage: Stage-7 + Stage: Stage-6 Move Operator files: hdfs directory: true #### A masked pattern was here #### - Stage: Stage-9 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((UDFToDouble(key) % 3.0) = 1.0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), 1 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-10 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((UDFToDouble(key) % 3.0) = 2.0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), 2 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - PREHOOK: query: create table union_top as select * from (select key, 0 as value from src where key % 3 == 0 limit 3)a union all @@ -756,98 +576,112 @@ select * from (select key, 2 as value from src where key % 3 == 2 limit 3)c POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-9, Stage-10 - Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 - Stage-5 - Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 - Stage-3 depends on stages: Stage-0 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 Stage-4 - Stage-6 - Stage-7 depends on stages: Stage-6 - Stage-9 is a root stage - Stage-10 is a root stage + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 + Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1-subquery1:_u1-subquery1-subquery1:a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) % 3.0) = 0.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 0 (type: int) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), 0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Union - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.union_top + Union + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.union_top TableScan - Union - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.union_top + alias: null-subquery1-subquery2:_u1-subquery1-subquery2:b:src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((UDFToDouble(key) % 3.0) = 1.0) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 3 + Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.union_top TableScan - Union - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.union_top + alias: null-subquery2:_u1-subquery2:c:src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((UDFToDouble(key) % 3.0) = 2.0) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 2 (type: int) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 3 + Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.union_top - Stage: Stage-8 + Stage: Stage-7 Conditional Operator - Stage: Stage-5 + Stage: Stage-4 Move Operator files: hdfs directory: true @@ -863,10 +697,10 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.union_top - Stage: Stage-3 + Stage: Stage-2 Stats-Aggr Operator - Stage: Stage-4 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan @@ -878,7 +712,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.union_top - Stage: Stage-6 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan @@ -890,90 +724,12 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.union_top - Stage: Stage-7 + Stage: Stage-6 Move Operator files: hdfs directory: true #### A masked pattern was here #### - Stage: Stage-9 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((UDFToDouble(key) % 3.0) = 1.0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), 1 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-10 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((UDFToDouble(key) % 3.0) = 2.0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), 2 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - PREHOOK: query: insert into table union_top select * from (select key, 0 as value from src where key % 3 == 0 limit 3)a union all @@ -992,7 +748,7 @@ select * from (select key, 2 as value from src where key % 3 == 2 limit 3)c POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@union_top -POSTHOOK: Lineage: union_top.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: union_top.key EXPRESSION [(src)null-subquery1-subquery1:_u1-subquery1-subquery1:a:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery2:_u1-subquery1-subquery2:b:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:_u1-subquery2:c:src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: union_top.value EXPRESSION [] PREHOOK: query: select * from union_top PREHOOK: type: QUERY @@ -1029,98 +785,112 @@ select * from (select key, 2 as value from src where key % 3 == 2 limit 3)c POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-9, Stage-10 - Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 - Stage-5 - Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 - Stage-3 depends on stages: Stage-0 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 Stage-4 - Stage-6 - Stage-7 depends on stages: Stage-6 - Stage-9 is a root stage - Stage-10 is a root stage + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 + Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - alias: src + alias: null-subquery1-subquery1:_u1-subquery1-subquery1:a:src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) % 3.0) = 0.0) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), 0 (type: int) + outputColumnNames: key, value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), 0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: + Union + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.union_top TableScan - Union - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.union_top - TableScan - Union - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.union_top + alias: null-subquery1-subquery2:_u1-subquery1-subquery2:b:src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((UDFToDouble(key) % 3.0) = 1.0) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 1 (type: int) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 3 + Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.union_top TableScan - Union - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.union_top + alias: null-subquery2:_u1-subquery2:c:src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((UDFToDouble(key) % 3.0) = 2.0) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), 2 (type: int) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 3 + Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: int) + outputColumnNames: key, value + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 90 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.union_top - Stage: Stage-8 + Stage: Stage-7 Conditional Operator - Stage: Stage-5 + Stage: Stage-4 Move Operator files: hdfs directory: true @@ -1136,10 +906,10 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.union_top - Stage: Stage-3 + Stage: Stage-2 Stats-Aggr Operator - Stage: Stage-4 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan @@ -1151,7 +921,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.union_top - Stage: Stage-6 + Stage: Stage-5 Map Reduce Map Operator Tree: TableScan @@ -1163,90 +933,12 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.union_top - Stage: Stage-7 + Stage: Stage-6 Move Operator files: hdfs directory: true #### A masked pattern was here #### - Stage: Stage-9 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((UDFToDouble(key) % 3.0) = 1.0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), 1 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-10 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((UDFToDouble(key) % 3.0) = 2.0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), 2 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - PREHOOK: query: insert overwrite table union_top select * from (select key, 0 as value from src where key % 3 == 0 limit 3)a union all @@ -1265,7 +957,7 @@ select * from (select key, 2 as value from src where key % 3 == 2 limit 3)c POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@union_top -POSTHOOK: Lineage: union_top.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: union_top.key EXPRESSION [(src)null-subquery1-subquery1:_u1-subquery1-subquery1:a:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery1-subquery2:_u1-subquery1-subquery2:b:src.FieldSchema(name:key, type:string, comment:default), (src)null-subquery2:_u1-subquery2:c:src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: union_top.value EXPRESSION [] PREHOOK: query: select * from union_top PREHOOK: type: QUERY @@ -1353,14 +1045,8 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@union_top_view #### A masked pattern was here #### -165 0 238 1 -255 0 -27 0 -278 2 311 2 -409 1 -484 1 86 2 PREHOOK: query: drop table union_top PREHOOK: type: DROPTABLE diff --git a/ql/src/test/results/clientpositive/union_view.q.out b/ql/src/test/results/clientpositive/union_view.q.out index c55dee6..4b7602e 100644 --- a/ql/src/test/results/clientpositive/union_view.q.out +++ b/ql/src/test/results/clientpositive/union_view.q.out @@ -60,7 +60,7 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 86 (type: int), value (type: string), '1' (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE ListSink @@ -81,7 +81,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 86 (type: int), value (type: string), '2' (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink @@ -102,7 +102,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 86 (type: int), value (type: string), '3' (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: key, value, ds Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE ListSink @@ -126,7 +126,7 @@ STAGE PLANS: filterExpr: (ds = '1') (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -148,9 +148,11 @@ STAGE PLANS: filterExpr: (ds = '1') (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -162,15 +164,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -193,7 +199,7 @@ STAGE PLANS: filterExpr: (ds = '2') (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -215,9 +221,11 @@ STAGE PLANS: filterExpr: (ds = '2') (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -229,15 +237,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -260,7 +272,7 @@ STAGE PLANS: filterExpr: (ds = '3') (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -282,9 +294,11 @@ STAGE PLANS: filterExpr: (ds = '3') (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -296,15 +310,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -332,7 +350,7 @@ STAGE PLANS: predicate: (key = 86) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -350,7 +368,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src_union_1 + alias: src_union_view-subquery1-subquery1:subq-subquery1-subquery1:src_union_1 filterExpr: ((key = 86) and (ds = '1')) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -358,13 +376,13 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 86 (type: int), _col1 (type: string), '1' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: 86 (type: int), value (type: string), '1' (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -374,7 +392,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: src_union_2 + alias: src_union_view-subquery1-subquery2:subq-subquery1-subquery2:src_union_2 filterExpr: ((key = 86) and (ds = '1')) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -382,13 +400,13 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 86 (type: int), _col1 (type: string), '1' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: 86 (type: int), value (type: string), '1' (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -398,7 +416,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: src_union_3 + alias: src_union_view-subquery2:subq-subquery2:src_union_3 filterExpr: ((key = 86) and (ds = '1')) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -406,13 +424,13 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 86 (type: int), _col1 (type: string), '1' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: 86 (type: int), value (type: string), '1' (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -445,7 +463,7 @@ STAGE PLANS: predicate: (key = 86) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -463,7 +481,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src_union_1 + alias: src_union_view-subquery1-subquery1:subq-subquery1-subquery1:src_union_1 filterExpr: ((key = 86) and (ds = '2')) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -471,13 +489,13 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 86 (type: int), _col1 (type: string), '2' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: 86 (type: int), value (type: string), '2' (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -487,7 +505,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: src_union_2 + alias: src_union_view-subquery1-subquery2:subq-subquery1-subquery2:src_union_2 filterExpr: ((key = 86) and (ds = '2')) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -495,13 +513,13 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 86 (type: int), _col1 (type: string), '2' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: 86 (type: int), value (type: string), '2' (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -511,7 +529,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: src_union_3 + alias: src_union_view-subquery2:subq-subquery2:src_union_3 filterExpr: ((key = 86) and (ds = '2')) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -519,13 +537,13 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 86 (type: int), _col1 (type: string), '2' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: 86 (type: int), value (type: string), '2' (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -558,7 +576,7 @@ STAGE PLANS: predicate: (key = 86) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -576,7 +594,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src_union_1 + alias: src_union_view-subquery1-subquery1:subq-subquery1-subquery1:src_union_1 filterExpr: ((key = 86) and (ds = '3')) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -584,13 +602,13 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 86 (type: int), _col1 (type: string), '3' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: 86 (type: int), value (type: string), '3' (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -600,7 +618,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: src_union_2 + alias: src_union_view-subquery1-subquery2:subq-subquery1-subquery2:src_union_2 filterExpr: ((key = 86) and (ds = '3')) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -608,13 +626,13 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 86 (type: int), _col1 (type: string), '3' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: 86 (type: int), value (type: string), '3' (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -624,7 +642,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: src_union_3 + alias: src_union_view-subquery2:subq-subquery2:src_union_3 filterExpr: ((key = 86) and (ds = '3')) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -632,13 +650,13 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 86 (type: int), _col1 (type: string), '3' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: 86 (type: int), value (type: string), '3' (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -675,7 +693,7 @@ STAGE PLANS: predicate: (key = 86) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -693,7 +711,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src_union_1 + alias: src_union_view-subquery1-subquery1:subq-subquery1-subquery1:src_union_1 filterExpr: ((key = 86) and ds is not null) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -701,21 +719,21 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), ds (type: string) - outputColumnNames: _col1, _col2 + outputColumnNames: value, ds Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col1, _col2 + expressions: ds (type: string), value (type: string) + outputColumnNames: ds, value Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: string) + key expressions: ds (type: string) sort order: + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src_union_2 + alias: src_union_view-subquery1-subquery2:subq-subquery1-subquery2:src_union_2 filterExpr: ((key = 86) and ds is not null) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -723,21 +741,21 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), ds (type: string) - outputColumnNames: _col1, _col2 + outputColumnNames: value, ds Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col1, _col2 + expressions: ds (type: string), value (type: string) + outputColumnNames: ds, value Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: string) + key expressions: ds (type: string) sort order: + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan - alias: src_union_3 + alias: src_union_view-subquery2:subq-subquery2:src_union_3 filterExpr: ((key = 86) and ds is not null) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -745,23 +763,23 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), ds (type: string) - outputColumnNames: _col1, _col2 + outputColumnNames: value, ds Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col1, _col2 + expressions: ds (type: string), value (type: string) + outputColumnNames: ds, value Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: string) + key expressions: ds (type: string) sort order: + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Reduce Operator Tree: Select Operator - expressions: 86 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: 86 (type: int), VALUE.value (type: string), KEY.reducesinkkey0 (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -781,7 +799,7 @@ STAGE PLANS: predicate: (key = 86) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -805,7 +823,7 @@ STAGE PLANS: predicate: (key = 86) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -850,7 +868,7 @@ STAGE PLANS: filterExpr: (ds = '1') (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -868,19 +886,21 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src_union_1 + alias: src_union_view-subquery1-subquery1:subq-subquery1-subquery1:src_union_1 filterExpr: (ds = '1') (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '1' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -889,7 +909,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src_union_2 + alias: src_union_view-subquery1-subquery2:subq-subquery1-subquery2:src_union_2 filterExpr: (ds = '1') (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -897,14 +917,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: '1' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -913,7 +935,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src_union_3 + alias: src_union_view-subquery2:subq-subquery2:src_union_3 filterExpr: (ds = '1') (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -921,14 +943,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: '1' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -940,15 +964,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -971,7 +999,7 @@ STAGE PLANS: filterExpr: (ds = '2') (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -989,7 +1017,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src_union_1 + alias: src_union_view-subquery1-subquery1:subq-subquery1-subquery1:src_union_1 filterExpr: (ds = '2') (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -997,14 +1025,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: '2' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -1013,19 +1043,21 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src_union_2 + alias: src_union_view-subquery1-subquery2:subq-subquery1-subquery2:src_union_2 filterExpr: (ds = '2') (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '2' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -1034,7 +1066,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src_union_3 + alias: src_union_view-subquery2:subq-subquery2:src_union_3 filterExpr: (ds = '2') (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -1042,14 +1074,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: '2' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -1061,15 +1095,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1092,7 +1130,7 @@ STAGE PLANS: filterExpr: (ds = '3') (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -1110,7 +1148,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src_union_1 + alias: src_union_view-subquery1-subquery1:subq-subquery1-subquery1:src_union_1 filterExpr: (ds = '3') (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -1118,14 +1156,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: '3' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -1134,7 +1174,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src_union_2 + alias: src_union_view-subquery1-subquery2:subq-subquery1-subquery2:src_union_2 filterExpr: (ds = '3') (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -1142,14 +1182,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: '3' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -1158,19 +1200,21 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src_union_3 + alias: src_union_view-subquery2:subq-subquery2:src_union_3 filterExpr: (ds = '3') (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '3' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -1182,15 +1226,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1218,7 +1266,7 @@ STAGE PLANS: predicate: (key = 86) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -1236,7 +1284,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src_union_1 + alias: src_union_view-subquery1-subquery1:subq-subquery1-subquery1:src_union_1 filterExpr: ((key = 86) and (ds = '4')) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -1244,13 +1292,13 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 86 (type: int), _col1 (type: string), '4' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: 86 (type: int), value (type: string), '4' (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1260,7 +1308,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: src_union_2 + alias: src_union_view-subquery1-subquery2:subq-subquery1-subquery2:src_union_2 filterExpr: ((key = 86) and (ds = '4')) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -1268,13 +1316,13 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 86 (type: int), _col1 (type: string), '4' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: 86 (type: int), value (type: string), '4' (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1284,7 +1332,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: src_union_3 + alias: src_union_view-subquery2:subq-subquery2:src_union_3 filterExpr: ((key = 86) and (ds = '4')) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -1292,13 +1340,13 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 86 (type: int), _col1 (type: string), '4' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: 86 (type: int), value (type: string), '4' (type: string) + outputColumnNames: key, value, ds Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1330,7 +1378,7 @@ STAGE PLANS: filterExpr: (ds = '4') (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) - outputColumnNames: _col0, _col1 + outputColumnNames: _bucketname, _offsets File Output Operator compressed: false table: @@ -1348,7 +1396,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src_union_1 + alias: src_union_view-subquery1-subquery1:subq-subquery1-subquery1:src_union_1 filterExpr: (ds = '4') (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -1356,14 +1404,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: '4' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -1372,7 +1422,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src_union_2 + alias: src_union_view-subquery1-subquery2:subq-subquery1-subquery2:src_union_2 filterExpr: (ds = '4') (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -1380,14 +1430,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: '4' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -1396,19 +1448,21 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) TableScan - alias: src_union_3 + alias: src_union_view-subquery2:subq-subquery2:src_union_3 filterExpr: (ds = '4') (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '4' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: 1 (type: int) + outputColumnNames: $f0 Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -1420,15 +1474,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/unionall_unbalancedppd.q.out b/ql/src/test/results/clientpositive/unionall_unbalancedppd.q.out index 1562087..c443dfe 100644 --- a/ql/src/test/results/clientpositive/unionall_unbalancedppd.q.out +++ b/ql/src/test/results/clientpositive/unionall_unbalancedppd.q.out @@ -83,43 +83,51 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: union_all_bug_test_1 + alias: null-subquery1:a-subquery1:union_all_bug_test_1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (if(true, f1, f2) = 1) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: f1 (type: int) - outputColumnNames: _col0 + outputColumnNames: f1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: f1 (type: int) + outputColumnNames: f1 Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: union_all_bug_test_2 + alias: null-subquery2:a-subquery2:union_all_bug_test_2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: f1 (type: int) - outputColumnNames: _col0 + outputColumnNames: f1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Union Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: f1 (type: int) + outputColumnNames: f1 Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -380,20 +388,20 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: union_all_bug_test_1 + alias: null-subquery1:a-subquery1:union_all_bug_test_1 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (f1 = 1) (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 1 (type: int) - outputColumnNames: _col0 + outputColumnNames: f1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 1 (type: int) - outputColumnNames: _col0 + outputColumnNames: f1 Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -403,20 +411,20 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: union_all_bug_test_2 + alias: null-subquery2:a-subquery2:union_all_bug_test_2 Statistics: Num rows: 2 Data size: 2 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (f1 = 1) (type: boolean) Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 1 (type: int) - outputColumnNames: _col0 + outputColumnNames: f1 Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 1 (type: int) - outputColumnNames: _col0 + outputColumnNames: f1 Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -521,20 +529,20 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: union_all_bug_test_1 + alias: null-subquery1:a-subquery1:union_all_bug_test_1 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((if(true, f1, f2) = 1) and (f1 = 1)) (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 1 (type: int) - outputColumnNames: _col0 + outputColumnNames: f1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1 (type: int) - outputColumnNames: _col0 + outputColumnNames: f1 Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -544,20 +552,20 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan - alias: union_all_bug_test_2 + alias: null-subquery2:a-subquery2:union_all_bug_test_2 Statistics: Num rows: 2 Data size: 2 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator expressions: 1 (type: int) - outputColumnNames: _col0 + outputColumnNames: f1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Union Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1 (type: int) - outputColumnNames: _col0 + outputColumnNames: f1 Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vector_aggregate_9.q.out b/ql/src/test/results/clientpositive/vector_aggregate_9.q.out index f81816c..c7ade56 100644 --- a/ql/src/test/results/clientpositive/vector_aggregate_9.q.out +++ b/ql/src/test/results/clientpositive/vector_aggregate_9.q.out @@ -120,10 +120,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dc (type: decimal(38,18)) - outputColumnNames: _col0 + outputColumnNames: dc Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0), max(_col0), sum(_col0), avg(_col0) + aggregations: min(dc), max(dc), sum(dc), avg(dc) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE @@ -136,15 +136,19 @@ STAGE PLANS: Group By Operator aggregations: min(VALUE._col0), max(VALUE._col1), sum(VALUE._col2), avg(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 448 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 448 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 784 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: decimal(38,18)), $f1 (type: decimal(38,18)), $f2 (type: decimal(38,18)), $f3 (type: decimal(38,18)) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 784 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 784 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_aggregate_without_gby.q.out b/ql/src/test/results/clientpositive/vector_aggregate_without_gby.q.out index 1175cb8..68f5103 100644 --- a/ql/src/test/results/clientpositive/vector_aggregate_without_gby.q.out +++ b/ql/src/test/results/clientpositive/vector_aggregate_without_gby.q.out @@ -53,10 +53,10 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dt (type: int), greg_dt (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0), max(_col1) + aggregations: max($f0), max($f1) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: NONE @@ -69,15 +69,19 @@ STAGE PLANS: Group By Operator aggregations: max(VALUE._col0), max(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: int), $f1 (type: string) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_between_in.q.out b/ql/src/test/results/clientpositive/vector_between_in.q.out index a9b9a4b..8e41784 100644 --- a/ql/src/test/results/clientpositive/vector_between_in.q.out +++ b/ql/src/test/results/clientpositive/vector_between_in.q.out @@ -28,17 +28,17 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdate (type: date) - outputColumnNames: _col0 + outputColumnNames: cdate Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: date) + key expressions: cdate (type: date) sort order: + Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: date) - outputColumnNames: _col0 + outputColumnNames: cdate Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -88,15 +88,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -124,17 +128,17 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdecimal1 (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: cdecimal1 Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: decimal(20,10)) + key expressions: cdecimal1 (type: decimal(20,10)) sort order: + Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: cdecimal1 Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -184,15 +188,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -220,17 +228,17 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdate (type: date) - outputColumnNames: _col0 + outputColumnNames: cdate Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: date) + key expressions: cdate (type: date) sort order: + Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: date) - outputColumnNames: _col0 + outputColumnNames: cdate Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -266,17 +274,17 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdate (type: date) - outputColumnNames: _col0 + outputColumnNames: cdate Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: date) + key expressions: cdate (type: date) sort order: + Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: date) - outputColumnNames: _col0 + outputColumnNames: cdate Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -312,17 +320,17 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdecimal1 (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: cdecimal1 Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: decimal(20,10)) + key expressions: cdecimal1 (type: decimal(20,10)) sort order: + Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: cdecimal1 Statistics: Num rows: 6144 Data size: 1233808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -372,15 +380,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_binary_join_groupby.q.out b/ql/src/test/results/clientpositive/vector_binary_join_groupby.q.out index c3e4d52..22ad253 100644 --- a/ql/src/test/results/clientpositive/vector_binary_join_groupby.q.out +++ b/ql/src/test/results/clientpositive/vector_binary_join_groupby.q.out @@ -147,15 +147,19 @@ STAGE PLANS: 1 bin (type: binary) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24 Statistics: Num rows: 55 Data size: 16300 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8,_col9,_col10,_col14,_col15,_col16,_col17,_col18,_col19,_col20,_col21,_col22,_col23,_col24)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: boolean), _col7 (type: string), _col8 (type: timestamp), _col9 (type: decimal(4,2)), _col10 (type: binary), _col14 (type: tinyint), _col15 (type: smallint), _col16 (type: int), _col17 (type: bigint), _col18 (type: float), _col19 (type: double), _col20 (type: boolean), _col21 (type: string), _col22 (type: timestamp), _col23 (type: decimal(4,2)), _col24 (type: binary) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24 + Statistics: Num rows: 55 Data size: 16300 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8,_col9,_col10,_col14,_col15,_col16,_col17,_col18,_col19,_col20,_col21,_col22,_col23,_col24)) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -164,13 +168,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -213,11 +221,11 @@ STAGE PLANS: Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: bin (type: binary) - outputColumnNames: _col0 + outputColumnNames: bin Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: binary) + keys: bin (type: binary) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE @@ -233,11 +241,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: binary) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: bin, $f1 Statistics: Num rows: 50 Data size: 14819 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint), _col0 (type: binary) - outputColumnNames: _col0, _col1 + expressions: $f1 (type: bigint), bin (type: binary) + outputColumnNames: _o__c0, bin Statistics: Num rows: 50 Data size: 14819 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vector_bround.q.out b/ql/src/test/results/clientpositive/vector_bround.q.out index 85049a8..6e6df7a 100644 --- a/ql/src/test/results/clientpositive/vector_bround.q.out +++ b/ql/src/test/results/clientpositive/vector_bround.q.out @@ -51,7 +51,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 128 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: bround(v0) (type: double), bround(v1, 1) (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: _o__c0, _o__c1 Statistics: Num rows: 8 Data size: 128 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vector_bucket.q.out b/ql/src/test/results/clientpositive/vector_bucket.q.out index 7a6a4da..b622387 100644 --- a/ql/src/test/results/clientpositive/vector_bucket.q.out +++ b/ql/src/test/results/clientpositive/vector_bucket.q.out @@ -26,13 +26,13 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 26 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: tmp_values_col1 (type: string), tmp_values_col2 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: tmp_values_col1, tmp_values_col2 Statistics: Num rows: 1 Data size: 26 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Map-reduce partition columns: UDFToInteger(_col0) (type: int) + Map-reduce partition columns: UDFToInteger(tmp_values_col1) (type: int) Statistics: Num rows: 1 Data size: 26 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) + value expressions: tmp_values_col1 (type: string), tmp_values_col2 (type: string) Reduce Operator Tree: Select Operator expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string) diff --git a/ql/src/test/results/clientpositive/vector_cast_constant.q.java1.7.out b/ql/src/test/results/clientpositive/vector_cast_constant.q.java1.7.out index 9edd6f1..e1678ea 100644 --- a/ql/src/test/results/clientpositive/vector_cast_constant.q.java1.7.out +++ b/ql/src/test/results/clientpositive/vector_cast_constant.q.java1.7.out @@ -128,12 +128,12 @@ STAGE PLANS: alias: over1korc Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: i (type: int) - outputColumnNames: _col0 + expressions: i (type: int), 50 (type: int), 50.0 (type: double), 50 (type: decimal(10,0)) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(50), avg(50.0), avg(50) - keys: _col0 (type: int) + aggregations: avg($f1), avg($f2), avg($f3) + keys: $f0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE @@ -142,35 +142,39 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + value expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: avg(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2) keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: int), $f1 (type: double), $f2 (type: double), $f3 (type: decimal(6,4)) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: $f0 (type: int) sort order: + Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: decimal(14,4)) + value expressions: $f1 (type: double), $f2 (type: double), $f3 (type: decimal(6,4)) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: decimal(14,4)) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: KEY.reducesinkkey0 (type: int), VALUE.$f1 (type: double), VALUE.$f2 (type: double), VALUE.$f3 (type: decimal(6,4)) + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 diff --git a/ql/src/test/results/clientpositive/vector_char_2.q.out b/ql/src/test/results/clientpositive/vector_char_2.q.out index 880dd42..5baf30c 100644 --- a/ql/src/test/results/clientpositive/vector_char_2.q.out +++ b/ql/src/test/results/clientpositive/vector_char_2.q.out @@ -73,11 +73,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: char(20)), UDFToInteger(key) (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1), count() - keys: _col0 (type: char(20)) + aggregations: sum($f1), count() + keys: $f0 (type: char(20)) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE @@ -93,28 +93,32 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) keys: KEY._col0 (type: char(20)) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 250 Data size: 49500 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: char(20)), $f1 (type: bigint), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 250 Data size: 49500 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: char(20)) + key expressions: $f0 (type: char(20)) sort order: + Statistics: Num rows: 250 Data size: 49500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint), _col2 (type: bigint) + value expressions: $f1 (type: bigint), $f2 (type: bigint) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: char(20)), VALUE._col0 (type: bigint), VALUE._col1 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: KEY.reducesinkkey0 (type: char(20)), VALUE.$f1 (type: bigint), VALUE.$f2 (type: bigint) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 250 Data size: 49500 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 @@ -203,11 +207,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: char(20)), UDFToInteger(key) (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1), count() - keys: _col0 (type: char(20)) + aggregations: sum($f1), count() + keys: $f0 (type: char(20)) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE @@ -223,28 +227,32 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) keys: KEY._col0 (type: char(20)) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 250 Data size: 49500 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: char(20)), $f1 (type: bigint), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f2 + Statistics: Num rows: 250 Data size: 49500 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: char(20)) + key expressions: $f0 (type: char(20)) sort order: - Statistics: Num rows: 250 Data size: 49500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint), _col2 (type: bigint) + value expressions: $f1 (type: bigint), $f2 (type: bigint) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: char(20)), VALUE._col0 (type: bigint), VALUE._col1 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: KEY.reducesinkkey0 (type: char(20)), VALUE.$f1 (type: bigint), VALUE.$f2 (type: bigint) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 250 Data size: 49500 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 diff --git a/ql/src/test/results/clientpositive/vector_char_simple.q.out b/ql/src/test/results/clientpositive/vector_char_simple.q.out index a61cbc8..55e4c72 100644 --- a/ql/src/test/results/clientpositive/vector_char_simple.q.out +++ b/ql/src/test/results/clientpositive/vector_char_simple.q.out @@ -68,18 +68,18 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: char(10)), value (type: char(20)) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: char(10)) + key expressions: key (type: char(10)) sort order: + Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: char(20)) + value expressions: value (type: char(20)) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: char(10)), VALUE._col0 (type: char(20)) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: char(10)), VALUE.value (type: char(20)) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 @@ -161,18 +161,18 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: char(10)), value (type: char(20)) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: char(10)) + key expressions: key (type: char(10)) sort order: - Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: char(20)) + value expressions: value (type: char(20)) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: char(10)), VALUE._col0 (type: char(20)) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: char(10)), VALUE.value (type: char(20)) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 @@ -242,8 +242,13 @@ insert into table char_3 select cint from alltypesorc limit 10 POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 @@ -254,36 +259,33 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: CAST( cint AS CHAR(12) (type: char(12)) + outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.char_3 Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: CAST( _col0 AS CHAR(12) (type: char(12)) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat - serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde - name: default.char_3 + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -298,6 +300,26 @@ STAGE PLANS: Stage: Stage-2 Stats-Aggr Operator + Stage: Stage-3 + Merge File Operator + Map Operator Tree: + ORC File Merge Operator + merge level: stripe + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + + Stage: Stage-5 + Merge File Operator + Map Operator Tree: + ORC File Merge Operator + merge level: stripe + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: insert into table char_3 select cint from alltypesorc limit 10 PREHOOK: type: QUERY PREHOOK: Input: default@alltypesorc diff --git a/ql/src/test/results/clientpositive/vector_coalesce.q.out b/ql/src/test/results/clientpositive/vector_coalesce.q.out index 8cc8220..ac5379a 100644 --- a/ql/src/test/results/clientpositive/vector_coalesce.q.out +++ b/ql/src/test/results/clientpositive/vector_coalesce.q.out @@ -29,18 +29,18 @@ STAGE PLANS: predicate: cdouble is null (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cstring1 (type: string), cint (type: int), cfloat (type: float), csmallint (type: smallint), COALESCE(null,cstring1,cint,cfloat,csmallint) (type: string) - outputColumnNames: _col1, _col2, _col3, _col4, _col5 + expressions: COALESCE(null,cstring1,cint,cfloat,csmallint) (type: string), cfloat (type: float), cint (type: int), csmallint (type: smallint), cstring1 (type: string) + outputColumnNames: c, cfloat, cint, csmallint, cstring1 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: null (type: double), _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: smallint), _col5 (type: string) + key expressions: null (type: double), cstring1 (type: string), cint (type: int), cfloat (type: float), csmallint (type: smallint), c (type: string) sort order: ++++++ Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: null (type: double), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: int), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: smallint), KEY.reducesinkkey5 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: cdouble, cstring1, cint, cfloat, csmallint, c Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -112,18 +112,18 @@ STAGE PLANS: predicate: ctinyint is null (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cdouble (type: double), cint (type: int), COALESCE(null,(cdouble + log2(cint)),0) (type: double) - outputColumnNames: _col1, _col2, _col3 + expressions: COALESCE(null,(cdouble + log2(cint)),0) (type: double), cdouble (type: double), cint (type: int) + outputColumnNames: c, cdouble, cint Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: null (type: tinyint), _col1 (type: double), _col2 (type: int), _col3 (type: double) + key expressions: null (type: tinyint), cdouble (type: double), cint (type: int), c (type: double) sort order: ++++ Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: null (type: tinyint), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: int), KEY.reducesinkkey3 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: ctinyint, cdouble, cint, c Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -204,7 +204,7 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: null (type: float), null (type: bigint), 0.0 (type: float) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: cfloat, cbigint, c Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -277,17 +277,17 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), COALESCE(ctimestamp1,ctimestamp2) (type: timestamp) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: ctimestamp1, ctimestamp2, c Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: timestamp), _col1 (type: timestamp), _col2 (type: timestamp) + key expressions: ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), c (type: timestamp) sort order: +++ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: timestamp), KEY.reducesinkkey2 (type: timestamp) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: ctimestamp1, ctimestamp2, c Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 diff --git a/ql/src/test/results/clientpositive/vector_coalesce_2.q.out b/ql/src/test/results/clientpositive/vector_coalesce_2.q.out index a496f52..1dbc97c 100644 --- a/ql/src/test/results/clientpositive/vector_coalesce_2.q.out +++ b/ql/src/test/results/clientpositive/vector_coalesce_2.q.out @@ -41,11 +41,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 510 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: str2 (type: string), UDFToInteger(COALESCE(str1,0)) (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 4 Data size: 510 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string) + aggregations: sum($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 4 Data size: 510 Basic stats: COMPLETE Column stats: NONE @@ -60,11 +60,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 2 Data size: 255 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), round((UDFToDouble(_col1) / 60.0), 2) (type: double) - outputColumnNames: _col0, _col1 + expressions: $f0 (type: string), round((UDFToDouble($f1) / 60.0), 2) (type: double) + outputColumnNames: str2, result Statistics: Num rows: 2 Data size: 255 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -117,7 +117,7 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 510 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: COALESCE(str1,0) (type: string) - outputColumnNames: _col0 + outputColumnNames: result Statistics: Num rows: 4 Data size: 510 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -172,11 +172,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 510 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: str2 (type: string), UDFToInteger(COALESCE(str1,0)) (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 4 Data size: 510 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string) + aggregations: sum($f1) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 4 Data size: 510 Basic stats: COMPLETE Column stats: NONE @@ -192,11 +192,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 2 Data size: 255 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), round((UDFToDouble(_col1) / 60.0), 2) (type: double) - outputColumnNames: _col0, _col1 + expressions: $f0 (type: string), round((UDFToDouble($f1) / 60.0), 2) (type: double) + outputColumnNames: str2, result Statistics: Num rows: 2 Data size: 255 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -249,7 +249,7 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 510 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: COALESCE(str1,0) (type: string) - outputColumnNames: _col0 + outputColumnNames: result Statistics: Num rows: 4 Data size: 510 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vector_count_distinct.q.out b/ql/src/test/results/clientpositive/vector_count_distinct.q.out index b87b2c7..9b2688f 100644 --- a/ql/src/test/results/clientpositive/vector_count_distinct.q.out +++ b/ql/src/test/results/clientpositive/vector_count_distinct.q.out @@ -1252,11 +1252,11 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ws_order_number (type: int) - outputColumnNames: _col0 + outputColumnNames: ws_order_number Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0) - keys: _col0 (type: int) + aggregations: count(DISTINCT ws_order_number) + keys: ws_order_number (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE @@ -1269,15 +1269,19 @@ STAGE PLANS: Group By Operator aggregations: count(DISTINCT KEY._col0:0._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_data_types.q.out b/ql/src/test/results/clientpositive/vector_data_types.q.out index 3ed833b..6c1734d 100644 --- a/ql/src/test/results/clientpositive/vector_data_types.q.out +++ b/ql/src/test/results/clientpositive/vector_data_types.q.out @@ -114,17 +114,17 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float), d (type: double), bo (type: boolean), s (type: string), ts (type: timestamp), dec (type: decimal(4,2)), bin (type: binary) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: t, si, i, b, f, d, bo, s, ts, dec, bin Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int) + key expressions: t (type: tinyint), si (type: smallint), i (type: int) sort order: +++ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: boolean), _col7 (type: string), _col8 (type: timestamp), _col9 (type: decimal(4,2)), _col10 (type: binary) + value expressions: b (type: bigint), f (type: float), d (type: double), bo (type: boolean), s (type: string), ts (type: timestamp), dec (type: decimal(4,2)), bin (type: binary) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: boolean), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: decimal(4,2)), VALUE._col7 (type: binary) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE.b (type: bigint), VALUE.f (type: float), VALUE.d (type: double), VALUE.bo (type: boolean), VALUE.s (type: string), VALUE.ts (type: timestamp), VALUE.dec (type: decimal(4,2)), VALUE.bin (type: binary) + outputColumnNames: t, si, i, b, f, d, bo, s, ts, dec, bin Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 @@ -199,18 +199,18 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float), d (type: double), bo (type: boolean), s (type: string), ts (type: timestamp), dec (type: decimal(4,2)), bin (type: binary) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: t, si, i, b, f, d, bo, s, ts, dec, bin Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int) + key expressions: t (type: tinyint), si (type: smallint), i (type: int) sort order: +++ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: boolean), _col7 (type: string), _col8 (type: timestamp), _col9 (type: decimal(4,2)), _col10 (type: binary) + value expressions: b (type: bigint), f (type: float), d (type: double), bo (type: boolean), s (type: string), ts (type: timestamp), dec (type: decimal(4,2)), bin (type: binary) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: boolean), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: decimal(4,2)), VALUE._col7 (type: binary) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE.b (type: bigint), VALUE.f (type: float), VALUE.d (type: double), VALUE.bo (type: boolean), VALUE.s (type: string), VALUE.ts (type: timestamp), VALUE.dec (type: decimal(4,2)), VALUE.bin (type: binary) + outputColumnNames: t, si, i, b, f, d, bo, s, ts, dec, bin Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 diff --git a/ql/src/test/results/clientpositive/vector_date_1.q.out b/ql/src/test/results/clientpositive/vector_date_1.q.out index 7195b12..67376c0 100644 --- a/ql/src/test/results/clientpositive/vector_date_1.q.out +++ b/ql/src/test/results/clientpositive/vector_date_1.q.out @@ -89,18 +89,18 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dt1 (type: date), dt2 (type: date), (dt1 = dt1) (type: boolean), (dt1 <> dt2) (type: boolean), (dt1 <= dt1) (type: boolean), (dt1 <= dt2) (type: boolean), (dt1 < dt2) (type: boolean), (dt2 >= dt2) (type: boolean), (dt2 >= dt1) (type: boolean), (dt2 > dt1) (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + outputColumnNames: dt1, dt2, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9 Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: date) + key expressions: dt1 (type: date) sort order: + Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: date), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: boolean) + value expressions: dt2 (type: date), _o__c2 (type: boolean), _o__c3 (type: boolean), _o__c4 (type: boolean), _o__c5 (type: boolean), _o__c6 (type: boolean), _o__c7 (type: boolean), _o__c8 (type: boolean), _o__c9 (type: boolean) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: date), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean), VALUE._col3 (type: boolean), VALUE._col4 (type: boolean), VALUE._col5 (type: boolean), VALUE._col6 (type: boolean), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + expressions: KEY.reducesinkkey0 (type: date), VALUE.dt2 (type: date), VALUE._o__c2 (type: boolean), VALUE._o__c3 (type: boolean), VALUE._o__c4 (type: boolean), VALUE._o__c5 (type: boolean), VALUE._o__c6 (type: boolean), VALUE._o__c7 (type: boolean), VALUE._o__c8 (type: boolean), VALUE._o__c9 (type: boolean) + outputColumnNames: dt1, dt2, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9 Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -190,18 +190,18 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dt1 (type: date), dt2 (type: date), (dt1 <> dt1) (type: boolean), (dt1 = dt2) (type: boolean), (dt1 < dt1) (type: boolean), (dt1 >= dt2) (type: boolean), (dt1 > dt2) (type: boolean), (dt2 > dt2) (type: boolean), (dt2 <= dt1) (type: boolean), (dt2 < dt1) (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + outputColumnNames: dt1, dt2, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9 Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: date) + key expressions: dt1 (type: date) sort order: + Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: date), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: boolean) + value expressions: dt2 (type: date), _o__c2 (type: boolean), _o__c3 (type: boolean), _o__c4 (type: boolean), _o__c5 (type: boolean), _o__c6 (type: boolean), _o__c7 (type: boolean), _o__c8 (type: boolean), _o__c9 (type: boolean) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: date), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean), VALUE._col3 (type: boolean), VALUE._col4 (type: boolean), VALUE._col5 (type: boolean), VALUE._col6 (type: boolean), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + expressions: KEY.reducesinkkey0 (type: date), VALUE.dt2 (type: date), VALUE._o__c2 (type: boolean), VALUE._o__c3 (type: boolean), VALUE._o__c4 (type: boolean), VALUE._o__c5 (type: boolean), VALUE._o__c6 (type: boolean), VALUE._o__c7 (type: boolean), VALUE._o__c8 (type: boolean), VALUE._o__c9 (type: boolean) + outputColumnNames: dt1, dt2, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9 Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -293,18 +293,18 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dt1 (type: date), (dt1 <> 1970-01-01) (type: boolean), (dt1 >= 1970-01-01) (type: boolean), (dt1 > 1970-01-01) (type: boolean), (dt1 <= 2100-01-01) (type: boolean), (dt1 < 2100-01-01) (type: boolean), (1970-01-01 <> dt1) (type: boolean), (1970-01-01 <= dt1) (type: boolean), (1970-01-01 < dt1) (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: dt1, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8 Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: date) + key expressions: dt1 (type: date) sort order: + Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean) + value expressions: _o__c1 (type: boolean), _o__c2 (type: boolean), _o__c3 (type: boolean), _o__c4 (type: boolean), _o__c5 (type: boolean), _o__c6 (type: boolean), _o__c7 (type: boolean), _o__c8 (type: boolean) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: boolean), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean), VALUE._col3 (type: boolean), VALUE._col4 (type: boolean), VALUE._col5 (type: boolean), VALUE._col6 (type: boolean), VALUE._col7 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + expressions: KEY.reducesinkkey0 (type: date), VALUE._o__c1 (type: boolean), VALUE._o__c2 (type: boolean), VALUE._o__c3 (type: boolean), VALUE._o__c4 (type: boolean), VALUE._o__c5 (type: boolean), VALUE._o__c6 (type: boolean), VALUE._o__c7 (type: boolean), VALUE._o__c8 (type: boolean) + outputColumnNames: dt1, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8 Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -394,18 +394,18 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dt1 (type: date), (dt1 = 1970-01-01) (type: boolean), (dt1 <= 1970-01-01) (type: boolean), (dt1 < 1970-01-01) (type: boolean), (dt1 >= 2100-01-01) (type: boolean), (dt1 > 2100-01-01) (type: boolean), (1970-01-01 = dt1) (type: boolean), (1970-01-01 >= dt1) (type: boolean), (1970-01-01 > dt1) (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: dt1, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8 Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: date) + key expressions: dt1 (type: date) sort order: + Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean) + value expressions: _o__c1 (type: boolean), _o__c2 (type: boolean), _o__c3 (type: boolean), _o__c4 (type: boolean), _o__c5 (type: boolean), _o__c6 (type: boolean), _o__c7 (type: boolean), _o__c8 (type: boolean) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: boolean), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean), VALUE._col3 (type: boolean), VALUE._col4 (type: boolean), VALUE._col5 (type: boolean), VALUE._col6 (type: boolean), VALUE._col7 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + expressions: KEY.reducesinkkey0 (type: date), VALUE._o__c1 (type: boolean), VALUE._o__c2 (type: boolean), VALUE._o__c3 (type: boolean), VALUE._o__c4 (type: boolean), VALUE._o__c5 (type: boolean), VALUE._o__c6 (type: boolean), VALUE._o__c7 (type: boolean), VALUE._o__c8 (type: boolean) + outputColumnNames: dt1, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8 Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -500,18 +500,18 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dt1 (type: date), dt2 (type: date) - outputColumnNames: _col0, _col1 + outputColumnNames: dt1, dt2 Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: date) + key expressions: dt1 (type: date) sort order: + Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: date) + value expressions: dt2 (type: date) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: date) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: date), VALUE.dt2 (type: date) + outputColumnNames: dt1, dt2 Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -607,18 +607,18 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dt2 (type: date) - outputColumnNames: _col1 + outputColumnNames: dt2 Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: 2001-01-01 (type: date) sort order: + Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: date) + value expressions: dt2 (type: date) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: 2001-01-01 (type: date), VALUE._col0 (type: date) - outputColumnNames: _col0, _col1 + expressions: 2001-01-01 (type: date), VALUE.dt2 (type: date) + outputColumnNames: dt1, dt2 Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vector_decimal_1.q.out b/ql/src/test/results/clientpositive/vector_decimal_1.q.out index 7d0ff75..b1caea0 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_1.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_1.q.out @@ -51,17 +51,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToBoolean(t) (type: boolean) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: boolean) + key expressions: t (type: boolean) sort order: + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: boolean) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -105,17 +105,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToByte(t) (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: tinyint) + key expressions: t (type: tinyint) sort order: + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -159,17 +159,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToShort(t) (type: smallint) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: smallint) + key expressions: t (type: smallint) sort order: + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: smallint) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -213,17 +213,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(t) (type: int) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: t (type: int) sort order: + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -267,17 +267,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToLong(t) (type: bigint) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: bigint) + key expressions: t (type: bigint) sort order: + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: bigint) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -321,17 +321,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToFloat(t) (type: float) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: float) + key expressions: t (type: float) sort order: + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: float) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -375,17 +375,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(t) (type: double) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: double) + key expressions: t (type: double) sort order: + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: double) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -429,17 +429,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToString(t) (type: string) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: t (type: string) sort order: + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -483,17 +483,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CAST( t AS TIMESTAMP) (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: timestamp) + key expressions: t (type: timestamp) sort order: + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vector_decimal_10_0.q.out b/ql/src/test/results/clientpositive/vector_decimal_10_0.q.out index 6e8338f..13025f7 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_10_0.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_10_0.q.out @@ -51,17 +51,17 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(10,0)) - outputColumnNames: _col0 + outputColumnNames: dec Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: decimal(10,0)) + key expressions: dec (type: decimal(10,0)) sort order: + Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(10,0)) - outputColumnNames: _col0 + outputColumnNames: dec Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vector_decimal_2.q.out b/ql/src/test/results/clientpositive/vector_decimal_2.q.out index 8a4d53a..251f198 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_2.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_2.q.out @@ -40,17 +40,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToBoolean(t) (type: boolean) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: boolean) + key expressions: t (type: boolean) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: boolean) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -94,17 +94,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToByte(t) (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: tinyint) + key expressions: t (type: tinyint) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -148,17 +148,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToShort(t) (type: smallint) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: smallint) + key expressions: t (type: smallint) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: smallint) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -202,17 +202,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(t) (type: int) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: t (type: int) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -256,17 +256,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToLong(t) (type: bigint) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: bigint) + key expressions: t (type: bigint) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: bigint) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -310,17 +310,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToFloat(t) (type: float) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: float) + key expressions: t (type: float) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: float) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -364,17 +364,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(t) (type: double) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: double) + key expressions: t (type: double) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: double) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -418,17 +418,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToString(t) (type: string) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: t (type: string) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -483,17 +483,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToBoolean(t) (type: boolean) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: boolean) + key expressions: t (type: boolean) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: boolean) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -537,17 +537,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToByte(t) (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: tinyint) + key expressions: t (type: tinyint) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -591,17 +591,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToShort(t) (type: smallint) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: smallint) + key expressions: t (type: smallint) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: smallint) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -645,17 +645,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(t) (type: int) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: t (type: int) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -699,17 +699,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToLong(t) (type: bigint) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: bigint) + key expressions: t (type: bigint) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: bigint) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -753,17 +753,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToFloat(t) (type: float) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: float) + key expressions: t (type: float) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: float) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -807,17 +807,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(t) (type: double) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: double) + key expressions: t (type: double) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: double) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -861,17 +861,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToString(t) (type: string) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: t (type: string) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 + outputColumnNames: t Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -914,16 +914,16 @@ STAGE PLANS: alias: decimal_2 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 3.14 (type: decimal(3,2)) sort order: + - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: 3.14 (type: decimal(4,2)) - outputColumnNames: _col0 + outputColumnNames: c Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -966,16 +966,16 @@ STAGE PLANS: alias: decimal_2 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 3.14 (type: decimal(3,2)) sort order: + - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: 3.14 (type: decimal(4,2)) - outputColumnNames: _col0 + outputColumnNames: c Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -1018,16 +1018,16 @@ STAGE PLANS: alias: decimal_2 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 1355944339.1234567 (type: decimal(17,7)) sort order: + - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: 1355944339.1234567 (type: decimal(30,8)) - outputColumnNames: _col0 + outputColumnNames: c Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -1070,16 +1070,16 @@ STAGE PLANS: alias: decimal_2 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 1 (type: int) sort order: + - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: 1 (type: decimal(10,0)) - outputColumnNames: _col0 + outputColumnNames: c Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -1113,16 +1113,16 @@ STAGE PLANS: alias: decimal_2 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 1 (type: int) sort order: + - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: 1 (type: decimal(10,0)) - outputColumnNames: _col0 + outputColumnNames: c Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -1165,16 +1165,16 @@ STAGE PLANS: alias: decimal_2 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 3 (type: int) sort order: + - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: 3 (type: decimal(10,0)) - outputColumnNames: _col0 + outputColumnNames: c Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -1217,16 +1217,16 @@ STAGE PLANS: alias: decimal_2 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 3 (type: int) sort order: + - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: 3 (type: decimal(10,0)) - outputColumnNames: _col0 + outputColumnNames: c Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -1269,16 +1269,16 @@ STAGE PLANS: alias: decimal_2 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 3 (type: int) sort order: + - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: 3 (type: decimal(10,0)) - outputColumnNames: _col0 + outputColumnNames: c Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -1321,16 +1321,16 @@ STAGE PLANS: alias: decimal_2 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 3 (type: int) sort order: + - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: 3 (type: decimal(10,0)) - outputColumnNames: _col0 + outputColumnNames: c Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -1373,16 +1373,16 @@ STAGE PLANS: alias: decimal_2 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 1 (type: int) sort order: + - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: 1 (type: decimal(20,19)) - outputColumnNames: _col0 + outputColumnNames: c Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -1425,16 +1425,16 @@ STAGE PLANS: alias: decimal_2 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 0.99999999999999999999 (type: decimal(20,20)) sort order: + - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: 0.99999999999999999999 (type: decimal(20,20)) - outputColumnNames: _col0 + outputColumnNames: c Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vector_decimal_aggregate.q.out b/ql/src/test/results/clientpositive/vector_decimal_aggregate.q.out index 02c1c83..06ac89f 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_aggregate.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_aggregate.q.out @@ -49,11 +49,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), max(_col1), min(_col1), sum(_col1), count(_col2), max(_col2), min(_col2), sum(_col2), count() - keys: _col0 (type: int) + aggregations: count($f1), max($f1), min($f1), sum($f1), count($f2), max($f2), min($f2), sum($f2), count() + keys: $f0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE @@ -69,14 +69,14 @@ STAGE PLANS: aggregations: count(VALUE._col0), max(VALUE._col1), min(VALUE._col2), sum(VALUE._col3), count(VALUE._col4), max(VALUE._col5), min(VALUE._col6), sum(VALUE._col7), count(VALUE._col8) keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9 Statistics: Num rows: 6144 Data size: 1082530 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col9 > 1) (type: boolean) + predicate: ($f9 > 1) (type: boolean) Statistics: Num rows: 2048 Data size: 360843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: decimal(20,10)), _col3 (type: decimal(20,10)), _col4 (type: decimal(30,10)), _col5 (type: bigint), _col6 (type: decimal(23,14)), _col7 (type: decimal(23,14)), _col8 (type: decimal(33,14)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + expressions: $f0 (type: int), $f1 (type: bigint), $f2 (type: decimal(20,10)), $f3 (type: decimal(20,10)), $f4 (type: decimal(30,10)), $f5 (type: bigint), $f6 (type: decimal(23,14)), $f7 (type: decimal(23,14)), $f8 (type: decimal(33,14)) + outputColumnNames: cint, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8 Statistics: Num rows: 2048 Data size: 360843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -147,11 +147,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), max(_col1), min(_col1), sum(_col1), avg(_col1), stddev_pop(_col1), stddev_samp(_col1), count(_col2), max(_col2), min(_col2), sum(_col2), avg(_col2), stddev_pop(_col2), stddev_samp(_col2), count() - keys: _col0 (type: int) + aggregations: count($f1), max($f1), min($f1), sum($f1), avg($f1), stddev_pop($f1), stddev_samp($f1), count($f2), max($f2), min($f2), sum($f2), avg($f2), stddev_pop($f2), stddev_samp($f2), count() + keys: $f0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE @@ -167,14 +167,14 @@ STAGE PLANS: aggregations: count(VALUE._col0), max(VALUE._col1), min(VALUE._col2), sum(VALUE._col3), avg(VALUE._col4), stddev_pop(VALUE._col5), stddev_samp(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9), sum(VALUE._col10), avg(VALUE._col11), stddev_pop(VALUE._col12), stddev_samp(VALUE._col13), count(VALUE._col14) keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15 Statistics: Num rows: 6144 Data size: 1082530 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col15 > 1) (type: boolean) + predicate: ($f15 > 1) (type: boolean) Statistics: Num rows: 2048 Data size: 360843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: decimal(20,10)), _col3 (type: decimal(20,10)), _col4 (type: decimal(30,10)), _col5 (type: decimal(24,14)), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: decimal(23,14)), _col10 (type: decimal(23,14)), _col11 (type: decimal(33,14)), _col12 (type: decimal(27,18)), _col13 (type: double), _col14 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + expressions: $f0 (type: int), $f1 (type: bigint), $f2 (type: decimal(20,10)), $f3 (type: decimal(20,10)), $f4 (type: decimal(30,10)), $f5 (type: decimal(24,14)), $f6 (type: double), $f7 (type: double), $f8 (type: bigint), $f9 (type: decimal(23,14)), $f10 (type: decimal(23,14)), $f11 (type: decimal(33,14)), $f12 (type: decimal(27,18)), $f13 (type: double), $f14 (type: double) + outputColumnNames: cint, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14 Statistics: Num rows: 2048 Data size: 360843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vector_decimal_cast.q.out b/ql/src/test/results/clientpositive/vector_decimal_cast.q.out index 88c09d9..547a8d6 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_cast.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_cast.q.out @@ -18,7 +18,7 @@ STAGE PLANS: Statistics: Num rows: 768 Data size: 165122 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cint (type: int), cboolean1 (type: boolean), ctimestamp1 (type: timestamp), CAST( cdouble AS decimal(20,10)) (type: decimal(20,10)), CAST( cint AS decimal(23,14)) (type: decimal(23,14)), CAST( cboolean1 AS decimal(5,2)) (type: decimal(5,2)), CAST( ctimestamp1 AS decimal(15,0)) (type: decimal(15,0)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + outputColumnNames: cdouble, cint, cboolean1, ctimestamp1, _o__c4, _o__c5, _o__c6, _o__c7 Statistics: Num rows: 768 Data size: 165122 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 diff --git a/ql/src/test/results/clientpositive/vector_decimal_expressions.q.out b/ql/src/test/results/clientpositive/vector_decimal_expressions.q.out index 6369bc8..6ec03d5 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_expressions.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_expressions.q.out @@ -36,17 +36,17 @@ STAGE PLANS: Statistics: Num rows: 228 Data size: 39491 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cdecimal1 + cdecimal2) (type: decimal(25,14)), (cdecimal1 - (2 * cdecimal2)) (type: decimal(26,14)), ((UDFToDouble(cdecimal1) + 2.34) / UDFToDouble(cdecimal2)) (type: double), (UDFToDouble(cdecimal1) * (UDFToDouble(cdecimal2) / 3.4)) (type: double), (cdecimal1 % 10) (type: decimal(12,10)), UDFToInteger(cdecimal1) (type: int), UDFToShort(cdecimal2) (type: smallint), UDFToByte(cdecimal2) (type: tinyint), UDFToLong(cdecimal1) (type: bigint), UDFToBoolean(cdecimal1) (type: boolean), UDFToDouble(cdecimal2) (type: double), UDFToFloat(cdecimal1) (type: float), UDFToString(cdecimal2) (type: string), CAST( cdecimal1 AS TIMESTAMP) (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + outputColumnNames: c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14 Statistics: Num rows: 228 Data size: 39491 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: decimal(25,14)), _col1 (type: decimal(26,14)), _col2 (type: double), _col3 (type: double), _col4 (type: decimal(12,10)), _col5 (type: int), _col6 (type: smallint), _col7 (type: tinyint), _col8 (type: bigint), _col9 (type: boolean), _col10 (type: double), _col11 (type: float), _col12 (type: string), _col13 (type: timestamp) + key expressions: c1 (type: decimal(25,14)), c2 (type: decimal(26,14)), c3 (type: double), c4 (type: double), c5 (type: decimal(12,10)), c6 (type: int), c7 (type: smallint), c8 (type: tinyint), c9 (type: bigint), c10 (type: boolean), c11 (type: double), c12 (type: float), c13 (type: string), c14 (type: timestamp) sort order: ++++++++++++++ Statistics: Num rows: 228 Data size: 39491 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(25,14)), KEY.reducesinkkey1 (type: decimal(26,14)), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: double), KEY.reducesinkkey4 (type: decimal(12,10)), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: smallint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: bigint), KEY.reducesinkkey9 (type: boolean), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: string), KEY.reducesinkkey13 (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + outputColumnNames: c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14 Statistics: Num rows: 228 Data size: 39491 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 diff --git a/ql/src/test/results/clientpositive/vector_decimal_math_funcs.q.out b/ql/src/test/results/clientpositive/vector_decimal_math_funcs.q.out index ceaaee5..6b5b11e 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_math_funcs.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_math_funcs.q.out @@ -102,7 +102,7 @@ STAGE PLANS: Statistics: Num rows: 2048 Data size: 366958 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdecimal1 (type: decimal(20,10)), round(cdecimal1, 2) (type: decimal(13,2)), round(cdecimal1) (type: decimal(11,0)), floor(cdecimal1) (type: decimal(11,0)), ceil(cdecimal1) (type: decimal(11,0)), round(exp(cdecimal1), 58) (type: double), ln(cdecimal1) (type: double), log10(cdecimal1) (type: double), log2(cdecimal1) (type: double), log2((UDFToDouble(cdecimal1) - 15601.0)) (type: double), log(2.0, cdecimal1) (type: double), power(log2(cdecimal1), 2.0) (type: double), power(log2(cdecimal1), 2.0) (type: double), sqrt(cdecimal1) (type: double), abs(cdecimal1) (type: decimal(20,10)), sin(cdecimal1) (type: double), asin(cdecimal1) (type: double), cos(cdecimal1) (type: double), acos(cdecimal1) (type: double), atan(cdecimal1) (type: double), degrees(cdecimal1) (type: double), radians(cdecimal1) (type: double), cdecimal1 (type: decimal(20,10)), (- cdecimal1) (type: decimal(20,10)), sign(cdecimal1) (type: int), cos(((- sin(log(cdecimal1))) + 3.14159)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25 + outputColumnNames: cdecimal1, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20, _o__c21, _o__c22, _o__c23, _o__c24, _o__c25 Statistics: Num rows: 2048 Data size: 366958 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vector_decimal_precision.q.out b/ql/src/test/results/clientpositive/vector_decimal_precision.q.out index 16f2e3f..03dc729 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_precision.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_precision.q.out @@ -562,10 +562,10 @@ STAGE PLANS: Statistics: Num rows: 75 Data size: 3472 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: dec Statistics: Num rows: 75 Data size: 3472 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), sum(_col0) + aggregations: avg(dec), sum(dec) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE @@ -578,15 +578,19 @@ STAGE PLANS: Group By Operator aggregations: avg(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: decimal(24,14)), $f1 (type: decimal(30,10)) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_decimal_round.q.out b/ql/src/test/results/clientpositive/vector_decimal_round.q.out index 25e5cfa..41d4b47 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_round.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_round.q.out @@ -49,17 +49,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(10,0)), round(dec, -1) (type: decimal(11,0)) - outputColumnNames: _col0, _col1 + outputColumnNames: dec, _o__c1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: decimal(10,0)) + key expressions: dec (type: decimal(10,0)) sort order: + Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(11,0)) + value expressions: _o__c1 (type: decimal(11,0)) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: decimal(10,0)), VALUE._col0 (type: decimal(11,0)) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: decimal(10,0)), VALUE._o__c1 (type: decimal(11,0)) + outputColumnNames: dec, _o__c1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -102,18 +102,18 @@ STAGE PLANS: alias: decimal_tbl_txt Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: dec (type: decimal(10,0)) - outputColumnNames: _col0 + expressions: round(dec, -1) (type: decimal(11,0)), dec (type: decimal(10,0)) + outputColumnNames: (tok_function round (tok_table_or_col dec) (- 1)), dec Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: round(_col0, (- 1)) (type: decimal(11,0)) + key expressions: (tok_function round (tok_table_or_col dec) (- 1)) (type: decimal(11,0)) sort order: + Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(10,0)) + value expressions: dec (type: decimal(10,0)) Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: decimal(10,0)), KEY.reducesinkkey0 (type: decimal(11,0)) - outputColumnNames: _col0, _col1 + expressions: VALUE.dec (type: decimal(10,0)), KEY.reducesinkkey0 (type: decimal(11,0)) + outputColumnNames: dec, _o__c1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -185,17 +185,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(10,0)), round(dec, -1) (type: decimal(11,0)) - outputColumnNames: _col0, _col1 + outputColumnNames: dec, _o__c1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: decimal(10,0)) + key expressions: dec (type: decimal(10,0)) sort order: + Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(11,0)) + value expressions: _o__c1 (type: decimal(11,0)) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: decimal(10,0)), VALUE._col0 (type: decimal(11,0)) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: decimal(10,0)), VALUE._o__c1 (type: decimal(11,0)) + outputColumnNames: dec, _o__c1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -238,18 +238,18 @@ STAGE PLANS: alias: decimal_tbl_rc Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: dec (type: decimal(10,0)) - outputColumnNames: _col0 + expressions: round(dec, -1) (type: decimal(11,0)), dec (type: decimal(10,0)) + outputColumnNames: (tok_function round (tok_table_or_col dec) (- 1)), dec Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: round(_col0, (- 1)) (type: decimal(11,0)) + key expressions: (tok_function round (tok_table_or_col dec) (- 1)) (type: decimal(11,0)) sort order: + Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(10,0)) + value expressions: dec (type: decimal(10,0)) Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: decimal(10,0)), KEY.reducesinkkey0 (type: decimal(11,0)) - outputColumnNames: _col0, _col1 + expressions: VALUE.dec (type: decimal(10,0)), KEY.reducesinkkey0 (type: decimal(11,0)) + outputColumnNames: dec, _o__c1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -321,18 +321,18 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(10,0)), round(dec, -1) (type: decimal(11,0)) - outputColumnNames: _col0, _col1 + outputColumnNames: dec, _o__c1 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: decimal(10,0)) + key expressions: dec (type: decimal(10,0)) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(11,0)) + value expressions: _o__c1 (type: decimal(11,0)) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: decimal(10,0)), VALUE._col0 (type: decimal(11,0)) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: decimal(10,0)), VALUE._o__c1 (type: decimal(11,0)) + outputColumnNames: dec, _o__c1 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -375,19 +375,19 @@ STAGE PLANS: alias: decimal_tbl_orc Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: dec (type: decimal(10,0)) - outputColumnNames: _col0 + expressions: round(dec, -1) (type: decimal(11,0)), dec (type: decimal(10,0)) + outputColumnNames: (tok_function round (tok_table_or_col dec) (- 1)), dec Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: round(_col0, (- 1)) (type: decimal(11,0)) + key expressions: (tok_function round (tok_table_or_col dec) (- 1)) (type: decimal(11,0)) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(10,0)) + value expressions: dec (type: decimal(10,0)) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: decimal(10,0)), KEY.reducesinkkey0 (type: decimal(11,0)) - outputColumnNames: _col0, _col1 + expressions: VALUE.dec (type: decimal(10,0)), KEY.reducesinkkey0 (type: decimal(11,0)) + outputColumnNames: dec, _o__c1 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vector_decimal_round_2.q.out b/ql/src/test/results/clientpositive/vector_decimal_round_2.q.out index 0151b04..6b72a31 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_round_2.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_round_2.q.out @@ -71,18 +71,18 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: round(dec) (type: decimal(21,0)), round(dec, 0) (type: decimal(21,0)), round(dec, 1) (type: decimal(22,1)), round(dec, 2) (type: decimal(23,2)), round(dec, 3) (type: decimal(24,3)), round(dec, -1) (type: decimal(21,0)), round(dec, -2) (type: decimal(21,0)), round(dec, -3) (type: decimal(21,0)), round(dec, -4) (type: decimal(21,0)), round(dec, -5) (type: decimal(21,0)), round(dec, -6) (type: decimal(21,0)), round(dec, -7) (type: decimal(21,0)), round(dec, -8) (type: decimal(21,0)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + outputColumnNames: d, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: decimal(21,0)) + key expressions: d (type: decimal(21,0)) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(21,0)), _col2 (type: decimal(22,1)), _col3 (type: decimal(23,2)), _col4 (type: decimal(24,3)), _col5 (type: decimal(21,0)), _col6 (type: decimal(21,0)), _col7 (type: decimal(21,0)), _col8 (type: decimal(21,0)), _col9 (type: decimal(21,0)), _col10 (type: decimal(21,0)), _col11 (type: decimal(21,0)), _col12 (type: decimal(21,0)) + value expressions: _o__c1 (type: decimal(21,0)), _o__c2 (type: decimal(22,1)), _o__c3 (type: decimal(23,2)), _o__c4 (type: decimal(24,3)), _o__c5 (type: decimal(21,0)), _o__c6 (type: decimal(21,0)), _o__c7 (type: decimal(21,0)), _o__c8 (type: decimal(21,0)), _o__c9 (type: decimal(21,0)), _o__c10 (type: decimal(21,0)), _o__c11 (type: decimal(21,0)), _o__c12 (type: decimal(21,0)) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: decimal(21,0)), VALUE._col0 (type: decimal(21,0)), VALUE._col1 (type: decimal(22,1)), VALUE._col2 (type: decimal(23,2)), VALUE._col3 (type: decimal(24,3)), VALUE._col4 (type: decimal(21,0)), VALUE._col5 (type: decimal(21,0)), VALUE._col6 (type: decimal(21,0)), VALUE._col7 (type: decimal(21,0)), VALUE._col8 (type: decimal(21,0)), VALUE._col9 (type: decimal(21,0)), VALUE._col10 (type: decimal(21,0)), VALUE._col11 (type: decimal(21,0)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + expressions: KEY.reducesinkkey0 (type: decimal(21,0)), VALUE._o__c1 (type: decimal(21,0)), VALUE._o__c2 (type: decimal(22,1)), VALUE._o__c3 (type: decimal(23,2)), VALUE._o__c4 (type: decimal(24,3)), VALUE._o__c5 (type: decimal(21,0)), VALUE._o__c6 (type: decimal(21,0)), VALUE._o__c7 (type: decimal(21,0)), VALUE._o__c8 (type: decimal(21,0)), VALUE._o__c9 (type: decimal(21,0)), VALUE._o__c10 (type: decimal(21,0)), VALUE._o__c11 (type: decimal(21,0)), VALUE._o__c12 (type: decimal(21,0)) + outputColumnNames: d, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -177,18 +177,18 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: round(pos) (type: decimal(21,0)), round(pos, 0) (type: decimal(21,0)), round(pos, 1) (type: decimal(22,1)), round(pos, 2) (type: decimal(23,2)), round(pos, 3) (type: decimal(24,3)), round(pos, 4) (type: decimal(25,4)), round(pos, -1) (type: decimal(21,0)), round(pos, -2) (type: decimal(21,0)), round(pos, -3) (type: decimal(21,0)), round(pos, -4) (type: decimal(21,0)), round(neg) (type: decimal(21,0)), round(neg, 0) (type: decimal(21,0)), round(neg, 1) (type: decimal(22,1)), round(neg, 2) (type: decimal(23,2)), round(neg, 3) (type: decimal(24,3)), round(neg, 4) (type: decimal(25,4)), round(neg, -1) (type: decimal(21,0)), round(neg, -2) (type: decimal(21,0)), round(neg, -3) (type: decimal(21,0)), round(neg, -4) (type: decimal(21,0)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19 + outputColumnNames: p, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19 Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: decimal(21,0)) + key expressions: p (type: decimal(21,0)) sort order: + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(21,0)), _col2 (type: decimal(22,1)), _col3 (type: decimal(23,2)), _col4 (type: decimal(24,3)), _col5 (type: decimal(25,4)), _col6 (type: decimal(21,0)), _col7 (type: decimal(21,0)), _col8 (type: decimal(21,0)), _col9 (type: decimal(21,0)), _col10 (type: decimal(21,0)), _col11 (type: decimal(21,0)), _col12 (type: decimal(22,1)), _col13 (type: decimal(23,2)), _col14 (type: decimal(24,3)), _col15 (type: decimal(25,4)), _col16 (type: decimal(21,0)), _col17 (type: decimal(21,0)), _col18 (type: decimal(21,0)), _col19 (type: decimal(21,0)) + value expressions: _o__c1 (type: decimal(21,0)), _o__c2 (type: decimal(22,1)), _o__c3 (type: decimal(23,2)), _o__c4 (type: decimal(24,3)), _o__c5 (type: decimal(25,4)), _o__c6 (type: decimal(21,0)), _o__c7 (type: decimal(21,0)), _o__c8 (type: decimal(21,0)), _o__c9 (type: decimal(21,0)), _o__c10 (type: decimal(21,0)), _o__c11 (type: decimal(21,0)), _o__c12 (type: decimal(22,1)), _o__c13 (type: decimal(23,2)), _o__c14 (type: decimal(24,3)), _o__c15 (type: decimal(25,4)), _o__c16 (type: decimal(21,0)), _o__c17 (type: decimal(21,0)), _o__c18 (type: decimal(21,0)), _o__c19 (type: decimal(21,0)) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: decimal(21,0)), VALUE._col0 (type: decimal(21,0)), VALUE._col1 (type: decimal(22,1)), VALUE._col2 (type: decimal(23,2)), VALUE._col3 (type: decimal(24,3)), VALUE._col4 (type: decimal(25,4)), VALUE._col5 (type: decimal(21,0)), VALUE._col6 (type: decimal(21,0)), VALUE._col7 (type: decimal(21,0)), VALUE._col8 (type: decimal(21,0)), VALUE._col9 (type: decimal(21,0)), VALUE._col10 (type: decimal(21,0)), VALUE._col11 (type: decimal(22,1)), VALUE._col12 (type: decimal(23,2)), VALUE._col13 (type: decimal(24,3)), VALUE._col14 (type: decimal(25,4)), VALUE._col15 (type: decimal(21,0)), VALUE._col16 (type: decimal(21,0)), VALUE._col17 (type: decimal(21,0)), VALUE._col18 (type: decimal(21,0)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19 + expressions: KEY.reducesinkkey0 (type: decimal(21,0)), VALUE._o__c1 (type: decimal(21,0)), VALUE._o__c2 (type: decimal(22,1)), VALUE._o__c3 (type: decimal(23,2)), VALUE._o__c4 (type: decimal(24,3)), VALUE._o__c5 (type: decimal(25,4)), VALUE._o__c6 (type: decimal(21,0)), VALUE._o__c7 (type: decimal(21,0)), VALUE._o__c8 (type: decimal(21,0)), VALUE._o__c9 (type: decimal(21,0)), VALUE._o__c10 (type: decimal(21,0)), VALUE._o__c11 (type: decimal(21,0)), VALUE._o__c12 (type: decimal(22,1)), VALUE._o__c13 (type: decimal(23,2)), VALUE._o__c14 (type: decimal(24,3)), VALUE._o__c15 (type: decimal(25,4)), VALUE._o__c16 (type: decimal(21,0)), VALUE._o__c17 (type: decimal(21,0)), VALUE._o__c18 (type: decimal(21,0)), VALUE._o__c19 (type: decimal(21,0)) + outputColumnNames: p, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19 Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -309,19 +309,19 @@ STAGE PLANS: alias: decimal_tbl_3_orc Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: round(dec, -15) (type: decimal(21,0)), round(dec, -16) (type: decimal(21,0)), round(dec, -5) (type: decimal(21,0)), round(dec, -6) (type: decimal(21,0)), round(dec, -3) (type: decimal(21,0)), round(dec, -4) (type: decimal(21,0)), round(dec, -1) (type: decimal(21,0)), round(dec, -2) (type: decimal(21,0)), round(dec, 0) (type: decimal(21,0)), round(dec, 1) (type: decimal(22,1)), round(dec, 2) (type: decimal(23,2)), round(dec, 3) (type: decimal(24,3)), round(dec, -13) (type: decimal(21,0)), round(dec, 4) (type: decimal(25,4)), round(dec, 5) (type: decimal(26,5)), round(dec, 6) (type: decimal(27,6)), round(dec, 7) (type: decimal(28,7)), round(dec, 8) (type: decimal(29,8)), round(dec, 9) (type: decimal(30,9)), round(dec, 10) (type: decimal(31,10)), round(dec, 11) (type: decimal(32,11)), round(dec, 12) (type: decimal(33,12)), round(dec, 13) (type: decimal(34,13)), round(dec, -14) (type: decimal(21,0)), round(dec, 14) (type: decimal(35,14)), round(dec, 15) (type: decimal(36,15)), round(dec, 16) (type: decimal(37,16)), round(dec, -11) (type: decimal(21,0)), round(dec, -12) (type: decimal(21,0)), round(dec, -9) (type: decimal(21,0)), round(dec, -10) (type: decimal(21,0)), round(dec, -7) (type: decimal(21,0)), round(dec, -8) (type: decimal(21,0)) - outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col2, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col3, _col31, _col32, _col33, _col4, _col5, _col6, _col7, _col8, _col9 + expressions: round(dec, -16) (type: decimal(21,0)), round(dec, -5) (type: decimal(21,0)), round(dec, -6) (type: decimal(21,0)), round(dec, -3) (type: decimal(21,0)), round(dec, -4) (type: decimal(21,0)), round(dec, -1) (type: decimal(21,0)), round(dec, -2) (type: decimal(21,0)), round(dec, 0) (type: decimal(21,0)), round(dec, 1) (type: decimal(22,1)), round(dec, 2) (type: decimal(23,2)), round(dec, 3) (type: decimal(24,3)), round(dec, -13) (type: decimal(21,0)), round(dec, 4) (type: decimal(25,4)), round(dec, 5) (type: decimal(26,5)), round(dec, 6) (type: decimal(27,6)), round(dec, 7) (type: decimal(28,7)), round(dec, 8) (type: decimal(29,8)), round(dec, 9) (type: decimal(30,9)), round(dec, 10) (type: decimal(31,10)), round(dec, 11) (type: decimal(32,11)), round(dec, 12) (type: decimal(33,12)), round(dec, 13) (type: decimal(34,13)), round(dec, -14) (type: decimal(21,0)), round(dec, 14) (type: decimal(35,14)), round(dec, 15) (type: decimal(36,15)), round(dec, 16) (type: decimal(37,16)), round(dec, -11) (type: decimal(21,0)), round(dec, -12) (type: decimal(21,0)), round(dec, -9) (type: decimal(21,0)), round(dec, -10) (type: decimal(21,0)), round(dec, -7) (type: decimal(21,0)), round(dec, -8) (type: decimal(21,0)), round(dec, -15) (type: decimal(21,0)) + outputColumnNames: _o__c1, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c2, _o__c20, _o__c21, _o__c22, _o__c23, _o__c24, _o__c25, _o__c26, _o__c27, _o__c28, _o__c29, _o__c3, _o__c31, _o__c32, _o__c33, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, d Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: decimal(21,0)) + key expressions: d (type: decimal(21,0)) sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(21,0)), _col2 (type: decimal(21,0)), _col3 (type: decimal(21,0)), _col4 (type: decimal(21,0)), _col5 (type: decimal(21,0)), _col6 (type: decimal(21,0)), _col7 (type: decimal(21,0)), _col8 (type: decimal(21,0)), _col9 (type: decimal(21,0)), _col10 (type: decimal(21,0)), _col11 (type: decimal(21,0)), _col12 (type: decimal(21,0)), _col13 (type: decimal(21,0)), _col14 (type: decimal(21,0)), _col15 (type: decimal(21,0)), _col16 (type: decimal(21,0)), _col17 (type: decimal(22,1)), _col18 (type: decimal(23,2)), _col19 (type: decimal(24,3)), _col20 (type: decimal(25,4)), _col21 (type: decimal(26,5)), _col22 (type: decimal(27,6)), _col23 (type: decimal(28,7)), _col24 (type: decimal(29,8)), _col25 (type: decimal(30,9)), _col26 (type: decimal(31,10)), _col27 (type: decimal(32,11)), _col28 (type: decimal(33,12)), _col29 (type: decimal(34,13)), _col31 (type: decimal(35,14)), _col32 (type: decimal(36,15)), _col33 (type: decimal(37,16)) + value expressions: _o__c1 (type: decimal(21,0)), _o__c2 (type: decimal(21,0)), _o__c3 (type: decimal(21,0)), _o__c4 (type: decimal(21,0)), _o__c5 (type: decimal(21,0)), _o__c6 (type: decimal(21,0)), _o__c7 (type: decimal(21,0)), _o__c8 (type: decimal(21,0)), _o__c9 (type: decimal(21,0)), _o__c10 (type: decimal(21,0)), _o__c11 (type: decimal(21,0)), _o__c12 (type: decimal(21,0)), _o__c13 (type: decimal(21,0)), _o__c14 (type: decimal(21,0)), _o__c15 (type: decimal(21,0)), _o__c16 (type: decimal(21,0)), _o__c17 (type: decimal(22,1)), _o__c18 (type: decimal(23,2)), _o__c19 (type: decimal(24,3)), _o__c20 (type: decimal(25,4)), _o__c21 (type: decimal(26,5)), _o__c22 (type: decimal(27,6)), _o__c23 (type: decimal(28,7)), _o__c24 (type: decimal(29,8)), _o__c25 (type: decimal(30,9)), _o__c26 (type: decimal(31,10)), _o__c27 (type: decimal(32,11)), _o__c28 (type: decimal(33,12)), _o__c29 (type: decimal(34,13)), _o__c31 (type: decimal(35,14)), _o__c32 (type: decimal(36,15)), _o__c33 (type: decimal(37,16)) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: decimal(21,0)), VALUE._col0 (type: decimal(21,0)), VALUE._col1 (type: decimal(21,0)), VALUE._col2 (type: decimal(21,0)), VALUE._col3 (type: decimal(21,0)), VALUE._col4 (type: decimal(21,0)), VALUE._col5 (type: decimal(21,0)), VALUE._col6 (type: decimal(21,0)), VALUE._col7 (type: decimal(21,0)), VALUE._col8 (type: decimal(21,0)), VALUE._col9 (type: decimal(21,0)), VALUE._col10 (type: decimal(21,0)), VALUE._col11 (type: decimal(21,0)), VALUE._col12 (type: decimal(21,0)), VALUE._col13 (type: decimal(21,0)), VALUE._col14 (type: decimal(21,0)), VALUE._col15 (type: decimal(21,0)), VALUE._col16 (type: decimal(22,1)), VALUE._col17 (type: decimal(23,2)), VALUE._col18 (type: decimal(24,3)), VALUE._col19 (type: decimal(25,4)), VALUE._col20 (type: decimal(26,5)), VALUE._col21 (type: decimal(27,6)), VALUE._col22 (type: decimal(28,7)), VALUE._col23 (type: decimal(29,8)), VALUE._col24 (type: decimal(30,9)), VALUE._col25 (type: decimal(31,10)), VALUE._col26 (type: decimal(32,11)), VALUE._col27 (type: decimal(33,12)), VALUE._col28 (type: decimal(34,13)), VALUE._col28 (type: decimal(34,13)), VALUE._col29 (type: decimal(35,14)), VALUE._col30 (type: decimal(36,15)), VALUE._col31 (type: decimal(37,16)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33 + expressions: KEY.reducesinkkey0 (type: decimal(21,0)), VALUE._o__c1 (type: decimal(21,0)), VALUE._o__c2 (type: decimal(21,0)), VALUE._o__c3 (type: decimal(21,0)), VALUE._o__c4 (type: decimal(21,0)), VALUE._o__c5 (type: decimal(21,0)), VALUE._o__c6 (type: decimal(21,0)), VALUE._o__c7 (type: decimal(21,0)), VALUE._o__c8 (type: decimal(21,0)), VALUE._o__c9 (type: decimal(21,0)), VALUE._o__c10 (type: decimal(21,0)), VALUE._o__c11 (type: decimal(21,0)), VALUE._o__c12 (type: decimal(21,0)), VALUE._o__c13 (type: decimal(21,0)), VALUE._o__c14 (type: decimal(21,0)), VALUE._o__c15 (type: decimal(21,0)), VALUE._o__c16 (type: decimal(21,0)), VALUE._o__c17 (type: decimal(22,1)), VALUE._o__c18 (type: decimal(23,2)), VALUE._o__c19 (type: decimal(24,3)), VALUE._o__c20 (type: decimal(25,4)), VALUE._o__c21 (type: decimal(26,5)), VALUE._o__c22 (type: decimal(27,6)), VALUE._o__c23 (type: decimal(28,7)), VALUE._o__c24 (type: decimal(29,8)), VALUE._o__c25 (type: decimal(30,9)), VALUE._o__c26 (type: decimal(31,10)), VALUE._o__c27 (type: decimal(32,11)), VALUE._o__c28 (type: decimal(33,12)), VALUE._o__c29 (type: decimal(34,13)), VALUE._o__c29 (type: decimal(34,13)), VALUE._o__c31 (type: decimal(35,14)), VALUE._o__c32 (type: decimal(36,15)), VALUE._o__c33 (type: decimal(37,16)) + outputColumnNames: d, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20, _o__c21, _o__c22, _o__c23, _o__c24, _o__c25, _o__c26, _o__c27, _o__c28, _o__c29, _o__c30, _o__c31, _o__c32, _o__c33 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -431,19 +431,19 @@ STAGE PLANS: alias: decimal_tbl_4_orc Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: round(pos, 9) (type: decimal(30,9)), round(neg, 9) (type: decimal(30,9)) - outputColumnNames: _col0, _col1 + expressions: round(neg, 9) (type: decimal(30,9)), round(pos, 9) (type: decimal(30,9)) + outputColumnNames: _o__c1, p Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: decimal(30,9)) + key expressions: p (type: decimal(30,9)) sort order: + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(30,9)) + value expressions: _o__c1 (type: decimal(30,9)) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: decimal(30,9)), VALUE._col0 (type: decimal(30,9)), 1809242.315111134 (type: decimal(17,9)), -1809242.315111134 (type: decimal(17,9)) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: KEY.reducesinkkey0 (type: decimal(30,9)), VALUE._o__c1 (type: decimal(30,9)), 1809242.315111134 (type: decimal(17,9)), -1809242.315111134 (type: decimal(17,9)) + outputColumnNames: p, _o__c1, _o__c2, _o__c3 Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vector_decimal_udf.q.out b/ql/src/test/results/clientpositive/vector_decimal_udf.q.out index 91a585c..1d055a3 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_udf.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_udf.q.out @@ -67,7 +67,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key + key) (type: decimal(21,10)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -147,7 +147,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key + CAST( value AS decimal(10,0))) (type: decimal(21,10)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -227,7 +227,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) + (UDFToDouble(value) / 2.0)) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -307,7 +307,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) + 1.0) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -389,7 +389,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key - key) (type: decimal(21,10)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -469,7 +469,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key - CAST( value AS decimal(10,0))) (type: decimal(21,10)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -549,7 +549,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) - (UDFToDouble(value) / 2.0)) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -629,7 +629,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) - 1.0) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -711,7 +711,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key * key) (type: decimal(38,20)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -794,7 +794,7 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 1356 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 12 Data size: 1356 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -859,7 +859,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key * CAST( value AS decimal(10,0))) (type: decimal(31,10)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -939,7 +939,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) * (UDFToDouble(value) / 2.0)) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1019,7 +1019,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) * 2.0) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1101,7 +1101,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key / 0) (type: decimal(22,12)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 @@ -1147,7 +1147,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) / null) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 @@ -1195,7 +1195,7 @@ STAGE PLANS: Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key / key) (type: decimal(38,24)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1274,7 +1274,7 @@ STAGE PLANS: Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key / CAST( value AS decimal(10,0))) (type: decimal(31,21)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1343,7 +1343,7 @@ STAGE PLANS: Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) / (UDFToDouble(value) / 2.0)) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1409,7 +1409,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (1.0 + (UDFToDouble(key) / 2.0)) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1491,7 +1491,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: abs(key) (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1574,11 +1574,11 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1), count(_col1), avg(_col1) - keys: _col0 (type: int) + aggregations: sum($f1), count($f1), avg($f1) + keys: $f0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE @@ -1594,11 +1594,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1), avg(VALUE._col2) keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), (_col1 / CAST( _col2 AS decimal(19,0))) (type: decimal(38,23)), _col3 (type: decimal(24,14)), _col1 (type: decimal(30,10)) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: $f0 (type: int), ($f1 / CAST( $f2 AS decimal(19,0))) (type: decimal(38,23)), $f3 (type: decimal(24,14)), $f1 (type: decimal(30,10)) + outputColumnNames: value, _o__c1, _o__c2, _o__c3 Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1612,14 +1612,14 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: value (type: int) sort order: + Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(38,23)), _col2 (type: decimal(24,14)), _col3 (type: decimal(30,10)) + value expressions: _o__c1 (type: decimal(38,23)), _o__c2 (type: decimal(24,14)), _o__c3 (type: decimal(30,10)) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: decimal(38,23)), VALUE._col1 (type: decimal(24,14)), VALUE._col2 (type: decimal(30,10)) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: KEY.reducesinkkey0 (type: int), VALUE._o__c1 (type: decimal(38,23)), VALUE._o__c2 (type: decimal(24,14)), VALUE._o__c3 (type: decimal(30,10)) + outputColumnNames: value, _o__c1, _o__c2, _o__c3 Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1679,7 +1679,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (- key) (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1761,7 +1761,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1830,7 +1830,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ceil(key) (type: decimal(11,0)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1912,7 +1912,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: floor(key) (type: decimal(11,0)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1994,7 +1994,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: round(key, 2) (type: decimal(13,2)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2076,7 +2076,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: power(key, 2) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2157,7 +2157,7 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ((key + 1) % (key / 2)) (type: decimal(22,12)) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2239,11 +2239,11 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev(_col1), variance(_col1) - keys: _col0 (type: int) + aggregations: stddev($f1), variance($f1) + keys: $f0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE @@ -2259,15 +2259,19 @@ STAGE PLANS: aggregations: stddev(VALUE._col0), variance(VALUE._col1) keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: int), $f1 (type: double), $f2 (type: double) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2319,11 +2323,11 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(_col1), var_samp(_col1) - keys: _col0 (type: int) + aggregations: stddev_samp($f1), var_samp($f1) + keys: $f0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE @@ -2339,15 +2343,19 @@ STAGE PLANS: aggregations: stddev_samp(VALUE._col0), var_samp(VALUE._col1) keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: int), $f1 (type: double), $f2 (type: double) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2398,11 +2406,11 @@ STAGE PLANS: alias: decimal_udf Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + expressions: key (type: decimal(20,10)), 3 (type: int) + outputColumnNames: $f0, $f1 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: histogram_numeric(_col0, 3) + aggregations: histogram_numeric($f0, $f1) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -2414,15 +2422,19 @@ STAGE PLANS: Group By Operator aggregations: histogram_numeric(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: array>) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2458,10 +2470,10 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE @@ -2474,15 +2486,19 @@ STAGE PLANS: Group By Operator aggregations: min(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: decimal(20,10)) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2518,10 +2534,10 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE @@ -2534,15 +2550,19 @@ STAGE PLANS: Group By Operator aggregations: max(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: decimal(20,10)) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2578,10 +2598,10 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -2594,15 +2614,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_decimal_udf2.q.out b/ql/src/test/results/clientpositive/vector_decimal_udf2.q.out index 4f6d7f1..5cecad6 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_udf2.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_udf2.q.out @@ -72,7 +72,7 @@ STAGE PLANS: Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: NaN (type: double), NaN (type: double), 1.4711276743037347 (type: double), -0.8390715290764524 (type: double), -0.5440211108893698 (type: double), 0.6483608274590866 (type: double), 0.17453292519943295 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6 Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -130,7 +130,7 @@ STAGE PLANS: Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 22026.465794806718 (type: double), 2.302585092994046 (type: double), 2.302585092994046 (type: double), 1.0 (type: double), log(10, value) (type: double), log(value, 10) (type: double), 1.0 (type: double), 3.1622776601683795 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7 Statistics: Num rows: 19 Data size: 2148 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vector_distinct_2.q.out b/ql/src/test/results/clientpositive/vector_distinct_2.q.out index 4153155..9bf484e 100644 --- a/ql/src/test/results/clientpositive/vector_distinct_2.q.out +++ b/ql/src/test/results/clientpositive/vector_distinct_2.q.out @@ -124,10 +124,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s (type: string), t (type: tinyint) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: tinyint) + keys: $f0 (type: string), $f1 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE @@ -141,15 +141,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: tinyint) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: tinyint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_elt.q.out b/ql/src/test/results/clientpositive/vector_elt.q.out index e3fa9ed..6e11173 100644 --- a/ql/src/test/results/clientpositive/vector_elt.q.out +++ b/ql/src/test/results/clientpositive/vector_elt.q.out @@ -22,7 +22,7 @@ STAGE PLANS: Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ((UDFToInteger(ctinyint) % 2) + 1) (type: int), cstring1 (type: string), cint (type: int), elt(((UDFToInteger(ctinyint) % 2) + 1), cstring1, cint) (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _o__c0, cstring1, cint, _o__c3 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -103,7 +103,7 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'defg' (type: string), 'cc' (type: string), 'abc' (type: string), '2' (type: string), '12345' (type: string), '123456789012' (type: string), '1.25' (type: string), '16.0' (type: string), null (type: string), null (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9 Statistics: Num rows: 12288 Data size: 8687616 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 diff --git a/ql/src/test/results/clientpositive/vector_groupby_3.q.out b/ql/src/test/results/clientpositive/vector_groupby_3.q.out index af7cb58..e0652bc 100644 --- a/ql/src/test/results/clientpositive/vector_groupby_3.q.out +++ b/ql/src/test/results/clientpositive/vector_groupby_3.q.out @@ -124,11 +124,11 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s (type: string), t (type: tinyint), b (type: bigint) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col2) - keys: _col0 (type: string), _col1 (type: tinyint) + aggregations: max($f2) + keys: $f0 (type: string), $f1 (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE @@ -144,15 +144,19 @@ STAGE PLANS: aggregations: max(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: tinyint) mode: mergepartial - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: string), $f1 (type: tinyint), $f2 (type: bigint) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_groupby_reduce.q.out b/ql/src/test/results/clientpositive/vector_groupby_reduce.q.out index edcb0b3..cf67607 100644 --- a/ql/src/test/results/clientpositive/vector_groupby_reduce.q.out +++ b/ql/src/test/results/clientpositive/vector_groupby_reduce.q.out @@ -240,10 +240,10 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ss_ticket_number (type: int) - outputColumnNames: _col0 + outputColumnNames: ss_ticket_number Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: ss_ticket_number (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE @@ -257,18 +257,22 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: ss_ticket_number Statistics: Num rows: 500 Data size: 44138 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 1760 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: ss_ticket_number (type: int) + outputColumnNames: ss_ticket_number + Statistics: Num rows: 500 Data size: 44138 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 20 Statistics: Num rows: 20 Data size: 1760 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 20 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -353,14 +357,14 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: store_sales + alias: a:store_sales Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ss_ticket_number (type: int) - outputColumnNames: _col0 + outputColumnNames: ss_ticket_number Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: ss_ticket_number (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE @@ -374,17 +378,17 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: ss_ticket_number Statistics: Num rows: 500 Data size: 44138 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) - keys: _col0 (type: int) + aggregations: min(ss_ticket_number) + keys: ss_ticket_number (type: int) mode: complete - outputColumnNames: _col0, _col1 + outputColumnNames: ss_ticket_number, $f1 Statistics: Num rows: 250 Data size: 22069 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int) - outputColumnNames: _col0 + expressions: $f1 (type: int) + outputColumnNames: _o__c0 Statistics: Num rows: 250 Data size: 22069 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 diff --git a/ql/src/test/results/clientpositive/vector_grouping_sets.q.out b/ql/src/test/results/clientpositive/vector_grouping_sets.q.out index 69d6187..6649ab6 100644 --- a/ql/src/test/results/clientpositive/vector_grouping_sets.q.out +++ b/ql/src/test/results/clientpositive/vector_grouping_sets.q.out @@ -121,32 +121,35 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s_store_id (type: string) - outputColumnNames: _col0 + outputColumnNames: s_store_id Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), '0' (type: string) + keys: s_store_id (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 24 Data size: 51264 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 24 Data size: 51264 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) + keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: s_store_id Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE - pruneGroupingSetId: true - File Output Operator - compressed: false + Select Operator + expressions: s_store_id (type: string) + outputColumnNames: s_store_id Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -196,27 +199,27 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s_store_id (type: string) - outputColumnNames: _col0 + outputColumnNames: s_store_id Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), '0' (type: string) + keys: s_store_id (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 24 Data size: 51264 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 24 Data size: 51264 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: s_store_id, GROUPING__ID Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + expressions: s_store_id (type: string), GROUPING__ID (type: int) + outputColumnNames: s_store_id, grouping__id Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vector_if_expr.q.out b/ql/src/test/results/clientpositive/vector_if_expr.q.out index 76f155b..654e55f 100644 --- a/ql/src/test/results/clientpositive/vector_if_expr.q.out +++ b/ql/src/test/results/clientpositive/vector_if_expr.q.out @@ -16,22 +16,22 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (cboolean1 is not null and cboolean1) (type: boolean) + predicate: (cboolean1 and cboolean1 is not null) (type: boolean) Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), if(cboolean1, 'first', 'second') (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: cboolean1, _o__c1 Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: boolean) + key expressions: cboolean1 (type: boolean) sort order: + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _o__c1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: boolean), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: boolean), VALUE._o__c1 (type: string) + outputColumnNames: cboolean1, _o__c1 Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vector_inner_join.q.out b/ql/src/test/results/clientpositive/vector_inner_join.q.out index 4775ae9..7a82d3f 100644 --- a/ql/src/test/results/clientpositive/vector_inner_join.q.out +++ b/ql/src/test/results/clientpositive/vector_inner_join.q.out @@ -127,11 +127,11 @@ STAGE PLANS: Stage: Stage-4 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:t1 + t1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:t1 + t1 TableScan alias: t1 Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -140,17 +140,12 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int) - outputColumnNames: _col0 + outputColumnNames: a Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + HashTable Sink Operator + keys: + 0 c (type: int) + 1 a (type: int) Stage: Stage-3 Map Reduce @@ -163,23 +158,27 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c (type: int) - outputColumnNames: _col0 + outputColumnNames: c Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 + 0 c (type: int) + 1 a (type: int) + outputColumnNames: c Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: c (type: int) + outputColumnNames: c Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work Execution mode: vectorized diff --git a/ql/src/test/results/clientpositive/vector_interval_1.q.out b/ql/src/test/results/clientpositive/vector_interval_1.q.out index a32583a..e5eb2cf 100644 --- a/ql/src/test/results/clientpositive/vector_interval_1.q.out +++ b/ql/src/test/results/clientpositive/vector_interval_1.q.out @@ -66,19 +66,19 @@ STAGE PLANS: alias: vector_interval_1 Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: str1 (type: string), CAST( str1 AS INTERVAL YEAR TO MONTH) (type: interval_year_month), CAST( str2 AS INTERVAL DAY TO SECOND) (type: interval_day_time) - outputColumnNames: _col0, _col2, _col4 + expressions: CAST( str1 AS INTERVAL YEAR TO MONTH) (type: interval_year_month), CAST( str2 AS INTERVAL DAY TO SECOND) (type: interval_day_time), str1 (type: string) + outputColumnNames: _o__c2, _o__c4, str1 Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: str1 (type: string) sort order: + Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: interval_year_month), _col4 (type: interval_day_time) + value expressions: _o__c2 (type: interval_year_month), _o__c4 (type: interval_day_time) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), 1-2 (type: interval_year_month), VALUE._col1 (type: interval_year_month), 1 02:03:04.000000000 (type: interval_day_time), VALUE._col3 (type: interval_day_time) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: KEY.reducesinkkey0 (type: string), 1-2 (type: interval_year_month), VALUE._o__c2 (type: interval_year_month), 1 02:03:04.000000000 (type: interval_day_time), VALUE._o__c4 (type: interval_day_time) + outputColumnNames: str1, _o__c1, _o__c2, _o__c3, _o__c4 Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -148,19 +148,19 @@ STAGE PLANS: alias: vector_interval_1 Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: dt (type: date), (CAST( str1 AS INTERVAL YEAR TO MONTH) + CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: interval_year_month), (1-2 + CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: interval_year_month), (CAST( str1 AS INTERVAL YEAR TO MONTH) - CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: interval_year_month), (1-2 - CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: interval_year_month) - outputColumnNames: _col0, _col2, _col3, _col5, _col6 + expressions: (CAST( str1 AS INTERVAL YEAR TO MONTH) + CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: interval_year_month), (1-2 + CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: interval_year_month), (CAST( str1 AS INTERVAL YEAR TO MONTH) - CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: interval_year_month), (1-2 - CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: interval_year_month), dt (type: date) + outputColumnNames: _o__c2, _o__c3, _o__c5, _o__c6, dt Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: date) + key expressions: dt (type: date) sort order: + Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: interval_year_month), _col3 (type: interval_year_month), _col5 (type: interval_year_month), _col6 (type: interval_year_month) + value expressions: _o__c2 (type: interval_year_month), _o__c3 (type: interval_year_month), _o__c5 (type: interval_year_month), _o__c6 (type: interval_year_month) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: date), 2-4 (type: interval_year_month), VALUE._col1 (type: interval_year_month), VALUE._col2 (type: interval_year_month), 0-0 (type: interval_year_month), VALUE._col4 (type: interval_year_month), VALUE._col5 (type: interval_year_month) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + expressions: KEY.reducesinkkey0 (type: date), 2-4 (type: interval_year_month), VALUE._o__c2 (type: interval_year_month), VALUE._o__c3 (type: interval_year_month), 0-0 (type: interval_year_month), VALUE._o__c5 (type: interval_year_month), VALUE._o__c6 (type: interval_year_month) + outputColumnNames: dt, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6 Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -236,19 +236,19 @@ STAGE PLANS: alias: vector_interval_1 Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: dt (type: date), (CAST( str2 AS INTERVAL DAY TO SECOND) + CAST( str2 AS INTERVAL DAY TO SECOND)) (type: interval_day_time), (1 02:03:04.000000000 + CAST( str2 AS INTERVAL DAY TO SECOND)) (type: interval_day_time), (CAST( str2 AS INTERVAL DAY TO SECOND) - CAST( str2 AS INTERVAL DAY TO SECOND)) (type: interval_day_time), (1 02:03:04.000000000 - CAST( str2 AS INTERVAL DAY TO SECOND)) (type: interval_day_time) - outputColumnNames: _col0, _col2, _col3, _col5, _col6 + expressions: (CAST( str2 AS INTERVAL DAY TO SECOND) + CAST( str2 AS INTERVAL DAY TO SECOND)) (type: interval_day_time), (1 02:03:04.000000000 + CAST( str2 AS INTERVAL DAY TO SECOND)) (type: interval_day_time), (CAST( str2 AS INTERVAL DAY TO SECOND) - CAST( str2 AS INTERVAL DAY TO SECOND)) (type: interval_day_time), (1 02:03:04.000000000 - CAST( str2 AS INTERVAL DAY TO SECOND)) (type: interval_day_time), dt (type: date) + outputColumnNames: _o__c2, _o__c3, _o__c5, _o__c6, dt Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: date) + key expressions: dt (type: date) sort order: + Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: interval_day_time), _col3 (type: interval_day_time), _col5 (type: interval_day_time), _col6 (type: interval_day_time) + value expressions: _o__c2 (type: interval_day_time), _o__c3 (type: interval_day_time), _o__c5 (type: interval_day_time), _o__c6 (type: interval_day_time) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: date), 2 04:06:08.000000000 (type: interval_day_time), VALUE._col1 (type: interval_day_time), VALUE._col2 (type: interval_day_time), 0 00:00:00.000000000 (type: interval_day_time), VALUE._col4 (type: interval_day_time), VALUE._col5 (type: interval_day_time) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + expressions: KEY.reducesinkkey0 (type: date), 2 04:06:08.000000000 (type: interval_day_time), VALUE._o__c2 (type: interval_day_time), VALUE._o__c3 (type: interval_day_time), 0 00:00:00.000000000 (type: interval_day_time), VALUE._o__c5 (type: interval_day_time), VALUE._o__c6 (type: interval_day_time) + outputColumnNames: dt, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6 Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -339,18 +339,18 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dt (type: date), (dt + 1-2) (type: date), (dt + CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: date), (1-2 + dt) (type: date), (CAST( str1 AS INTERVAL YEAR TO MONTH) + dt) (type: date), (dt - 1-2) (type: date), (dt - CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: date), (dt + 1 02:03:04.000000000) (type: timestamp), (dt + CAST( str2 AS INTERVAL DAY TO SECOND)) (type: timestamp), (1 02:03:04.000000000 + dt) (type: timestamp), (CAST( str2 AS INTERVAL DAY TO SECOND) + dt) (type: timestamp), (dt - 1 02:03:04.000000000) (type: timestamp), (dt - CAST( str2 AS INTERVAL DAY TO SECOND)) (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + outputColumnNames: dt, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12 Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: date) + key expressions: dt (type: date) sort order: + Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: date), _col2 (type: date), _col3 (type: date), _col4 (type: date), _col5 (type: date), _col6 (type: date), _col7 (type: timestamp), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: timestamp), _col11 (type: timestamp), _col12 (type: timestamp) + value expressions: _o__c1 (type: date), _o__c2 (type: date), _o__c3 (type: date), _o__c4 (type: date), _o__c5 (type: date), _o__c6 (type: date), _o__c7 (type: timestamp), _o__c8 (type: timestamp), _o__c9 (type: timestamp), _o__c10 (type: timestamp), _o__c11 (type: timestamp), _o__c12 (type: timestamp) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: date), VALUE._col1 (type: date), VALUE._col2 (type: date), VALUE._col3 (type: date), VALUE._col4 (type: date), VALUE._col5 (type: date), VALUE._col6 (type: timestamp), VALUE._col7 (type: timestamp), VALUE._col8 (type: timestamp), VALUE._col9 (type: timestamp), VALUE._col10 (type: timestamp), VALUE._col11 (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + expressions: KEY.reducesinkkey0 (type: date), VALUE._o__c1 (type: date), VALUE._o__c2 (type: date), VALUE._o__c3 (type: date), VALUE._o__c4 (type: date), VALUE._o__c5 (type: date), VALUE._o__c6 (type: date), VALUE._o__c7 (type: timestamp), VALUE._o__c8 (type: timestamp), VALUE._o__c9 (type: timestamp), VALUE._o__c10 (type: timestamp), VALUE._o__c11 (type: timestamp), VALUE._o__c12 (type: timestamp) + outputColumnNames: dt, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12 Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -453,18 +453,18 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts (type: timestamp), (ts + 1-2) (type: timestamp), (ts + CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: timestamp), (1-2 + ts) (type: timestamp), (CAST( str1 AS INTERVAL YEAR TO MONTH) + ts) (type: timestamp), (ts - 1-2) (type: timestamp), (ts - CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: timestamp), (ts + 1 02:03:04.000000000) (type: timestamp), (ts + CAST( str2 AS INTERVAL DAY TO SECOND)) (type: timestamp), (1 02:03:04.000000000 + ts) (type: timestamp), (CAST( str2 AS INTERVAL DAY TO SECOND) + ts) (type: timestamp), (ts - 1 02:03:04.000000000) (type: timestamp), (ts - CAST( str2 AS INTERVAL DAY TO SECOND)) (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + outputColumnNames: ts, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12 Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: timestamp) + key expressions: ts (type: timestamp) sort order: + Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: timestamp), _col2 (type: timestamp), _col3 (type: timestamp), _col4 (type: timestamp), _col5 (type: timestamp), _col6 (type: timestamp), _col7 (type: timestamp), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: timestamp), _col11 (type: timestamp), _col12 (type: timestamp) + value expressions: _o__c1 (type: timestamp), _o__c2 (type: timestamp), _o__c3 (type: timestamp), _o__c4 (type: timestamp), _o__c5 (type: timestamp), _o__c6 (type: timestamp), _o__c7 (type: timestamp), _o__c8 (type: timestamp), _o__c9 (type: timestamp), _o__c10 (type: timestamp), _o__c11 (type: timestamp), _o__c12 (type: timestamp) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: timestamp), VALUE._col0 (type: timestamp), VALUE._col1 (type: timestamp), VALUE._col2 (type: timestamp), VALUE._col3 (type: timestamp), VALUE._col4 (type: timestamp), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: timestamp), VALUE._col8 (type: timestamp), VALUE._col9 (type: timestamp), VALUE._col10 (type: timestamp), VALUE._col11 (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + expressions: KEY.reducesinkkey0 (type: timestamp), VALUE._o__c1 (type: timestamp), VALUE._o__c2 (type: timestamp), VALUE._o__c3 (type: timestamp), VALUE._o__c4 (type: timestamp), VALUE._o__c5 (type: timestamp), VALUE._o__c6 (type: timestamp), VALUE._o__c7 (type: timestamp), VALUE._o__c8 (type: timestamp), VALUE._o__c9 (type: timestamp), VALUE._o__c10 (type: timestamp), VALUE._o__c11 (type: timestamp), VALUE._o__c12 (type: timestamp) + outputColumnNames: ts, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12 Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -549,18 +549,18 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts (type: timestamp), (ts - ts) (type: interval_day_time), (2001-01-01 01:02:03.0 - ts) (type: interval_day_time), (ts - 2001-01-01 01:02:03.0) (type: interval_day_time) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: ts, _o__c1, _o__c2, _o__c3 Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: timestamp) + key expressions: ts (type: timestamp) sort order: + Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: interval_day_time), _col2 (type: interval_day_time), _col3 (type: interval_day_time) + value expressions: _o__c1 (type: interval_day_time), _o__c2 (type: interval_day_time), _o__c3 (type: interval_day_time) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: timestamp), VALUE._col0 (type: interval_day_time), VALUE._col1 (type: interval_day_time), VALUE._col2 (type: interval_day_time) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: KEY.reducesinkkey0 (type: timestamp), VALUE._o__c1 (type: interval_day_time), VALUE._o__c2 (type: interval_day_time), VALUE._o__c3 (type: interval_day_time) + outputColumnNames: ts, _o__c1, _o__c2, _o__c3 Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -627,18 +627,18 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dt (type: date), (dt - dt) (type: interval_day_time), (2001-01-01 - dt) (type: interval_day_time), (dt - 2001-01-01) (type: interval_day_time) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: dt, _o__c1, _o__c2, _o__c3 Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: date) + key expressions: dt (type: date) sort order: + Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: interval_day_time), _col2 (type: interval_day_time), _col3 (type: interval_day_time) + value expressions: _o__c1 (type: interval_day_time), _o__c2 (type: interval_day_time), _o__c3 (type: interval_day_time) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: interval_day_time), VALUE._col1 (type: interval_day_time), VALUE._col2 (type: interval_day_time) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: KEY.reducesinkkey0 (type: date), VALUE._o__c1 (type: interval_day_time), VALUE._o__c2 (type: interval_day_time), VALUE._o__c3 (type: interval_day_time) + outputColumnNames: dt, _o__c1, _o__c2, _o__c3 Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -711,18 +711,18 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dt (type: date), (ts - dt) (type: interval_day_time), (2001-01-01 01:02:03.0 - dt) (type: interval_day_time), (ts - 2001-01-01) (type: interval_day_time), (dt - ts) (type: interval_day_time), (dt - 2001-01-01 01:02:03.0) (type: interval_day_time), (2001-01-01 - ts) (type: interval_day_time) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: dt, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6 Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: date) + key expressions: dt (type: date) sort order: + Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: interval_day_time), _col2 (type: interval_day_time), _col3 (type: interval_day_time), _col4 (type: interval_day_time), _col5 (type: interval_day_time), _col6 (type: interval_day_time) + value expressions: _o__c1 (type: interval_day_time), _o__c2 (type: interval_day_time), _o__c3 (type: interval_day_time), _o__c4 (type: interval_day_time), _o__c5 (type: interval_day_time), _o__c6 (type: interval_day_time) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: interval_day_time), VALUE._col1 (type: interval_day_time), VALUE._col2 (type: interval_day_time), VALUE._col3 (type: interval_day_time), VALUE._col4 (type: interval_day_time), VALUE._col5 (type: interval_day_time) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + expressions: KEY.reducesinkkey0 (type: date), VALUE._o__c1 (type: interval_day_time), VALUE._o__c2 (type: interval_day_time), VALUE._o__c3 (type: interval_day_time), VALUE._o__c4 (type: interval_day_time), VALUE._o__c5 (type: interval_day_time), VALUE._o__c6 (type: interval_day_time) + outputColumnNames: dt, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6 Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vector_interval_2.q.out b/ql/src/test/results/clientpositive/vector_interval_2.q.out index 8528fa2..af42d15 100644 --- a/ql/src/test/results/clientpositive/vector_interval_2.q.out +++ b/ql/src/test/results/clientpositive/vector_interval_2.q.out @@ -123,18 +123,18 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 788 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: str1 (type: string), (CAST( str1 AS INTERVAL YEAR TO MONTH) = CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) <= CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) <= CAST( str2 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) < CAST( str2 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) >= CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str2 AS INTERVAL YEAR TO MONTH) >= CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str2 AS INTERVAL YEAR TO MONTH) > CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) <> CAST( str2 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) = 1-2) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) <= 1-2) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) <= 1-3) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) < 1-3) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) >= 1-2) (type: boolean), (CAST( str2 AS INTERVAL YEAR TO MONTH) >= 1-2) (type: boolean), (CAST( str2 AS INTERVAL YEAR TO MONTH) > 1-2) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) <> 1-3) (type: boolean), (1-2 = CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (1-2 <= CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (1-2 <= CAST( str2 AS INTERVAL YEAR TO MONTH)) (type: boolean), (1-2 < CAST( str2 AS INTERVAL YEAR TO MONTH)) (type: boolean), (1-2 >= CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (1-3 >= CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (1-3 > CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (1-2 <> CAST( str2 AS INTERVAL YEAR TO MONTH)) (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24 + outputColumnNames: str1, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20, _o__c21, _o__c22, _o__c23, _o__c24 Statistics: Num rows: 2 Data size: 788 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: str1 (type: string) sort order: + Statistics: Num rows: 2 Data size: 788 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: boolean), _col10 (type: boolean), _col11 (type: boolean), _col12 (type: boolean), _col13 (type: boolean), _col14 (type: boolean), _col15 (type: boolean), _col16 (type: boolean), _col17 (type: boolean), _col18 (type: boolean), _col19 (type: boolean), _col20 (type: boolean), _col21 (type: boolean), _col22 (type: boolean), _col23 (type: boolean), _col24 (type: boolean) + value expressions: _o__c1 (type: boolean), _o__c2 (type: boolean), _o__c3 (type: boolean), _o__c4 (type: boolean), _o__c5 (type: boolean), _o__c6 (type: boolean), _o__c7 (type: boolean), _o__c8 (type: boolean), _o__c9 (type: boolean), _o__c10 (type: boolean), _o__c11 (type: boolean), _o__c12 (type: boolean), _o__c13 (type: boolean), _o__c14 (type: boolean), _o__c15 (type: boolean), _o__c16 (type: boolean), _o__c17 (type: boolean), _o__c18 (type: boolean), _o__c19 (type: boolean), _o__c20 (type: boolean), _o__c21 (type: boolean), _o__c22 (type: boolean), _o__c23 (type: boolean), _o__c24 (type: boolean) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: boolean), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean), VALUE._col3 (type: boolean), VALUE._col4 (type: boolean), VALUE._col5 (type: boolean), VALUE._col6 (type: boolean), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean), VALUE._col9 (type: boolean), VALUE._col10 (type: boolean), VALUE._col11 (type: boolean), VALUE._col12 (type: boolean), VALUE._col13 (type: boolean), VALUE._col14 (type: boolean), VALUE._col15 (type: boolean), VALUE._col16 (type: boolean), VALUE._col17 (type: boolean), VALUE._col18 (type: boolean), VALUE._col19 (type: boolean), VALUE._col20 (type: boolean), VALUE._col21 (type: boolean), VALUE._col22 (type: boolean), VALUE._col23 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24 + expressions: KEY.reducesinkkey0 (type: string), VALUE._o__c1 (type: boolean), VALUE._o__c2 (type: boolean), VALUE._o__c3 (type: boolean), VALUE._o__c4 (type: boolean), VALUE._o__c5 (type: boolean), VALUE._o__c6 (type: boolean), VALUE._o__c7 (type: boolean), VALUE._o__c8 (type: boolean), VALUE._o__c9 (type: boolean), VALUE._o__c10 (type: boolean), VALUE._o__c11 (type: boolean), VALUE._o__c12 (type: boolean), VALUE._o__c13 (type: boolean), VALUE._o__c14 (type: boolean), VALUE._o__c15 (type: boolean), VALUE._o__c16 (type: boolean), VALUE._o__c17 (type: boolean), VALUE._o__c18 (type: boolean), VALUE._o__c19 (type: boolean), VALUE._o__c20 (type: boolean), VALUE._o__c21 (type: boolean), VALUE._o__c22 (type: boolean), VALUE._o__c23 (type: boolean), VALUE._o__c24 (type: boolean) + outputColumnNames: str1, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20, _o__c21, _o__c22, _o__c23, _o__c24 Statistics: Num rows: 2 Data size: 788 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -282,19 +282,19 @@ STAGE PLANS: alias: vector_interval_2 Statistics: Num rows: 2 Data size: 788 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: str1 (type: string), (CAST( str1 AS INTERVAL YEAR TO MONTH) <> CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str2 AS INTERVAL YEAR TO MONTH) <= 1-2) (type: boolean), (CAST( str2 AS INTERVAL YEAR TO MONTH) < 1-2) (type: boolean), (1-2 <> CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (1-2 >= CAST( str2 AS INTERVAL YEAR TO MONTH)) (type: boolean), (1-2 > CAST( str2 AS INTERVAL YEAR TO MONTH)) (type: boolean), (1-3 <= CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (1-3 < CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) >= CAST( str2 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) > CAST( str2 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str2 AS INTERVAL YEAR TO MONTH) <= CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str2 AS INTERVAL YEAR TO MONTH) < CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) <> 1-2) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) >= 1-3) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) > 1-3) (type: boolean) - outputColumnNames: _col0, _col1, _col10, _col11, _col13, _col14, _col15, _col16, _col17, _col2, _col3, _col4, _col5, _col7, _col8, _col9 + expressions: (CAST( str1 AS INTERVAL YEAR TO MONTH) <> CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str2 AS INTERVAL YEAR TO MONTH) <= 1-2) (type: boolean), (CAST( str2 AS INTERVAL YEAR TO MONTH) < 1-2) (type: boolean), (1-2 <> CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (1-2 >= CAST( str2 AS INTERVAL YEAR TO MONTH)) (type: boolean), (1-2 > CAST( str2 AS INTERVAL YEAR TO MONTH)) (type: boolean), (1-3 <= CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (1-3 < CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) >= CAST( str2 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) > CAST( str2 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str2 AS INTERVAL YEAR TO MONTH) <= CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str2 AS INTERVAL YEAR TO MONTH) < CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) <> 1-2) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) >= 1-3) (type: boolean), (CAST( str1 AS INTERVAL YEAR TO MONTH) > 1-3) (type: boolean), str1 (type: string) + outputColumnNames: _o__c1, _o__c10, _o__c11, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c2, _o__c3, _o__c4, _o__c5, _o__c7, _o__c8, _o__c9, str1 Statistics: Num rows: 2 Data size: 788 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: str1 (type: string) sort order: + Statistics: Num rows: 2 Data size: 788 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: boolean), _col10 (type: boolean), _col11 (type: boolean), _col13 (type: boolean), _col14 (type: boolean), _col15 (type: boolean), _col16 (type: boolean), _col17 (type: boolean) + value expressions: _o__c1 (type: boolean), _o__c2 (type: boolean), _o__c3 (type: boolean), _o__c4 (type: boolean), _o__c5 (type: boolean), _o__c7 (type: boolean), _o__c8 (type: boolean), _o__c9 (type: boolean), _o__c10 (type: boolean), _o__c11 (type: boolean), _o__c13 (type: boolean), _o__c14 (type: boolean), _o__c15 (type: boolean), _o__c16 (type: boolean), _o__c17 (type: boolean) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: boolean), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean), VALUE._col3 (type: boolean), VALUE._col4 (type: boolean), VALUE._col0 (type: boolean), VALUE._col5 (type: boolean), VALUE._col6 (type: boolean), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean), VALUE._col9 (type: boolean), VALUE._col5 (type: boolean), VALUE._col10 (type: boolean), VALUE._col11 (type: boolean), VALUE._col12 (type: boolean), VALUE._col13 (type: boolean), VALUE._col14 (type: boolean), VALUE._col10 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18 + expressions: KEY.reducesinkkey0 (type: string), VALUE._o__c1 (type: boolean), VALUE._o__c2 (type: boolean), VALUE._o__c3 (type: boolean), VALUE._o__c4 (type: boolean), VALUE._o__c5 (type: boolean), VALUE._o__c1 (type: boolean), VALUE._o__c7 (type: boolean), VALUE._o__c8 (type: boolean), VALUE._o__c9 (type: boolean), VALUE._o__c10 (type: boolean), VALUE._o__c11 (type: boolean), VALUE._o__c7 (type: boolean), VALUE._o__c13 (type: boolean), VALUE._o__c14 (type: boolean), VALUE._o__c15 (type: boolean), VALUE._o__c16 (type: boolean), VALUE._o__c17 (type: boolean), VALUE._o__c13 (type: boolean) + outputColumnNames: str1, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18 Statistics: Num rows: 2 Data size: 788 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -443,18 +443,18 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 788 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: str3 (type: string), (CAST( str3 AS INTERVAL DAY TO SECOND) = CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) <= CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) <= CAST( str4 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) < CAST( str4 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) >= CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str4 AS INTERVAL DAY TO SECOND) >= CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str4 AS INTERVAL DAY TO SECOND) > CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) <> CAST( str4 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) = 1 02:03:04.000000000) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) <= 1 02:03:04.000000000) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) <= 1 02:03:05.000000000) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) < 1 02:03:05.000000000) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) >= 1 02:03:04.000000000) (type: boolean), (CAST( str4 AS INTERVAL DAY TO SECOND) >= 1 02:03:04.000000000) (type: boolean), (CAST( str4 AS INTERVAL DAY TO SECOND) > 1 02:03:04.000000000) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) <> 1 02:03:05.000000000) (type: boolean), (1 02:03:04.000000000 = CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (1 02:03:04.000000000 <= CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (1 02:03:04.000000000 <= CAST( str4 AS INTERVAL DAY TO SECOND)) (type: boolean), (1 02:03:04.000000000 < CAST( str4 AS INTERVAL DAY TO SECOND)) (type: boolean), (1 02:03:04.000000000 >= CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (1 02:03:05.000000000 >= CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (1 02:03:05.000000000 > CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (1 02:03:04.000000000 <> CAST( str4 AS INTERVAL DAY TO SECOND)) (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24 + outputColumnNames: str3, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20, _o__c21, _o__c22, _o__c23, _o__c24 Statistics: Num rows: 2 Data size: 788 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: str3 (type: string) sort order: + Statistics: Num rows: 2 Data size: 788 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: boolean), _col10 (type: boolean), _col11 (type: boolean), _col12 (type: boolean), _col13 (type: boolean), _col14 (type: boolean), _col15 (type: boolean), _col16 (type: boolean), _col17 (type: boolean), _col18 (type: boolean), _col19 (type: boolean), _col20 (type: boolean), _col21 (type: boolean), _col22 (type: boolean), _col23 (type: boolean), _col24 (type: boolean) + value expressions: _o__c1 (type: boolean), _o__c2 (type: boolean), _o__c3 (type: boolean), _o__c4 (type: boolean), _o__c5 (type: boolean), _o__c6 (type: boolean), _o__c7 (type: boolean), _o__c8 (type: boolean), _o__c9 (type: boolean), _o__c10 (type: boolean), _o__c11 (type: boolean), _o__c12 (type: boolean), _o__c13 (type: boolean), _o__c14 (type: boolean), _o__c15 (type: boolean), _o__c16 (type: boolean), _o__c17 (type: boolean), _o__c18 (type: boolean), _o__c19 (type: boolean), _o__c20 (type: boolean), _o__c21 (type: boolean), _o__c22 (type: boolean), _o__c23 (type: boolean), _o__c24 (type: boolean) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: boolean), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean), VALUE._col3 (type: boolean), VALUE._col4 (type: boolean), VALUE._col5 (type: boolean), VALUE._col6 (type: boolean), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean), VALUE._col9 (type: boolean), VALUE._col10 (type: boolean), VALUE._col11 (type: boolean), VALUE._col12 (type: boolean), VALUE._col13 (type: boolean), VALUE._col14 (type: boolean), VALUE._col15 (type: boolean), VALUE._col16 (type: boolean), VALUE._col17 (type: boolean), VALUE._col18 (type: boolean), VALUE._col19 (type: boolean), VALUE._col20 (type: boolean), VALUE._col21 (type: boolean), VALUE._col22 (type: boolean), VALUE._col23 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24 + expressions: KEY.reducesinkkey0 (type: string), VALUE._o__c1 (type: boolean), VALUE._o__c2 (type: boolean), VALUE._o__c3 (type: boolean), VALUE._o__c4 (type: boolean), VALUE._o__c5 (type: boolean), VALUE._o__c6 (type: boolean), VALUE._o__c7 (type: boolean), VALUE._o__c8 (type: boolean), VALUE._o__c9 (type: boolean), VALUE._o__c10 (type: boolean), VALUE._o__c11 (type: boolean), VALUE._o__c12 (type: boolean), VALUE._o__c13 (type: boolean), VALUE._o__c14 (type: boolean), VALUE._o__c15 (type: boolean), VALUE._o__c16 (type: boolean), VALUE._o__c17 (type: boolean), VALUE._o__c18 (type: boolean), VALUE._o__c19 (type: boolean), VALUE._o__c20 (type: boolean), VALUE._o__c21 (type: boolean), VALUE._o__c22 (type: boolean), VALUE._o__c23 (type: boolean), VALUE._o__c24 (type: boolean) + outputColumnNames: str3, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20, _o__c21, _o__c22, _o__c23, _o__c24 Statistics: Num rows: 2 Data size: 788 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -602,19 +602,19 @@ STAGE PLANS: alias: vector_interval_2 Statistics: Num rows: 2 Data size: 788 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: str3 (type: string), (CAST( str3 AS INTERVAL DAY TO SECOND) <> CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str4 AS INTERVAL DAY TO SECOND) <= 1 02:03:04.000000000) (type: boolean), (CAST( str4 AS INTERVAL DAY TO SECOND) < 1 02:03:04.000000000) (type: boolean), (1 02:03:04.000000000 <> CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (1 02:03:04.000000000 >= CAST( str4 AS INTERVAL DAY TO SECOND)) (type: boolean), (1 02:03:04.000000000 > CAST( str4 AS INTERVAL DAY TO SECOND)) (type: boolean), (1 02:03:05.000000000 <= CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (1 02:03:05.000000000 < CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) >= CAST( str4 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) > CAST( str4 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str4 AS INTERVAL DAY TO SECOND) <= CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str4 AS INTERVAL DAY TO SECOND) < CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) <> 1 02:03:04.000000000) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) >= 1 02:03:05.000000000) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) > 1 02:03:05.000000000) (type: boolean) - outputColumnNames: _col0, _col1, _col10, _col11, _col13, _col14, _col15, _col16, _col17, _col2, _col3, _col4, _col5, _col7, _col8, _col9 + expressions: (CAST( str3 AS INTERVAL DAY TO SECOND) <> CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str4 AS INTERVAL DAY TO SECOND) <= 1 02:03:04.000000000) (type: boolean), (CAST( str4 AS INTERVAL DAY TO SECOND) < 1 02:03:04.000000000) (type: boolean), (1 02:03:04.000000000 <> CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (1 02:03:04.000000000 >= CAST( str4 AS INTERVAL DAY TO SECOND)) (type: boolean), (1 02:03:04.000000000 > CAST( str4 AS INTERVAL DAY TO SECOND)) (type: boolean), (1 02:03:05.000000000 <= CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (1 02:03:05.000000000 < CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) >= CAST( str4 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) > CAST( str4 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str4 AS INTERVAL DAY TO SECOND) <= CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str4 AS INTERVAL DAY TO SECOND) < CAST( str3 AS INTERVAL DAY TO SECOND)) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) <> 1 02:03:04.000000000) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) >= 1 02:03:05.000000000) (type: boolean), (CAST( str3 AS INTERVAL DAY TO SECOND) > 1 02:03:05.000000000) (type: boolean), str3 (type: string) + outputColumnNames: _o__c1, _o__c10, _o__c11, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c2, _o__c3, _o__c4, _o__c5, _o__c7, _o__c8, _o__c9, str3 Statistics: Num rows: 2 Data size: 788 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: str3 (type: string) sort order: + Statistics: Num rows: 2 Data size: 788 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: boolean), _col10 (type: boolean), _col11 (type: boolean), _col13 (type: boolean), _col14 (type: boolean), _col15 (type: boolean), _col16 (type: boolean), _col17 (type: boolean) + value expressions: _o__c1 (type: boolean), _o__c2 (type: boolean), _o__c3 (type: boolean), _o__c4 (type: boolean), _o__c5 (type: boolean), _o__c7 (type: boolean), _o__c8 (type: boolean), _o__c9 (type: boolean), _o__c10 (type: boolean), _o__c11 (type: boolean), _o__c13 (type: boolean), _o__c14 (type: boolean), _o__c15 (type: boolean), _o__c16 (type: boolean), _o__c17 (type: boolean) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: boolean), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean), VALUE._col3 (type: boolean), VALUE._col4 (type: boolean), VALUE._col0 (type: boolean), VALUE._col5 (type: boolean), VALUE._col6 (type: boolean), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean), VALUE._col9 (type: boolean), VALUE._col5 (type: boolean), VALUE._col10 (type: boolean), VALUE._col11 (type: boolean), VALUE._col12 (type: boolean), VALUE._col13 (type: boolean), VALUE._col14 (type: boolean), VALUE._col10 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18 + expressions: KEY.reducesinkkey0 (type: string), VALUE._o__c1 (type: boolean), VALUE._o__c2 (type: boolean), VALUE._o__c3 (type: boolean), VALUE._o__c4 (type: boolean), VALUE._o__c5 (type: boolean), VALUE._o__c1 (type: boolean), VALUE._o__c7 (type: boolean), VALUE._o__c8 (type: boolean), VALUE._o__c9 (type: boolean), VALUE._o__c10 (type: boolean), VALUE._o__c11 (type: boolean), VALUE._o__c7 (type: boolean), VALUE._o__c13 (type: boolean), VALUE._o__c14 (type: boolean), VALUE._o__c15 (type: boolean), VALUE._o__c16 (type: boolean), VALUE._o__c17 (type: boolean), VALUE._o__c13 (type: boolean) + outputColumnNames: str3, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18 Statistics: Num rows: 2 Data size: 788 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -754,17 +754,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ts Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: timestamp) + key expressions: ts (type: timestamp) sort order: + Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ts Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -899,17 +899,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ts Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: timestamp) + key expressions: ts (type: timestamp) sort order: + Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ts Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1034,17 +1034,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ts Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: timestamp) + key expressions: ts (type: timestamp) sort order: + Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ts Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1169,17 +1169,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ts Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: timestamp) + key expressions: ts (type: timestamp) sort order: + Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ts Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1316,17 +1316,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ts Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: timestamp) + key expressions: ts (type: timestamp) sort order: + Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ts Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1461,17 +1461,17 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ts Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: timestamp) + key expressions: ts (type: timestamp) sort order: + Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ts Statistics: Num rows: 1 Data size: 394 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vector_join30.q.out b/ql/src/test/results/clientpositive/vector_join30.q.out index cfe047d..42338ff 100644 --- a/ql/src/test/results/clientpositive/vector_join30.q.out +++ b/ql/src/test/results/clientpositive/vector_join30.q.out @@ -100,17 +100,21 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 275 Data size: 48400 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 275 Data size: 48400 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -128,13 +132,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-9 Map Reduce Local Work @@ -162,17 +170,21 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 275 Data size: 48400 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 275 Data size: 48400 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -201,17 +213,21 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 275 Data size: 48400 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 275 Data size: 48400 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -352,17 +368,21 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -380,13 +400,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-2 Map Reduce @@ -413,17 +437,21 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -561,17 +589,21 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -589,13 +621,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-2 Map Reduce @@ -622,17 +658,21 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -797,17 +837,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -825,13 +869,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-11 Map Reduce Local Work @@ -872,17 +920,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -925,17 +977,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -972,17 +1028,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -1182,17 +1242,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -1210,13 +1274,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-10 Map Reduce Local Work @@ -1257,17 +1325,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -1304,17 +1376,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -1506,17 +1582,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -1534,13 +1614,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-2 Map Reduce @@ -1575,17 +1659,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -1777,17 +1865,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -1805,13 +1897,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-2 Map Reduce @@ -1846,17 +1942,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -2048,17 +2148,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -2076,13 +2180,17 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-2 Map Reduce @@ -2117,17 +2225,21 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col2, _col3 Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: string), _col3 (type: string) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(hash(_col2,_col3)) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce diff --git a/ql/src/test/results/clientpositive/vector_join_nulls.q.out b/ql/src/test/results/clientpositive/vector_join_nulls.q.out index c1516f2..ca50c94 100644 --- a/ql/src/test/results/clientpositive/vector_join_nulls.q.out +++ b/ql/src/test/results/clientpositive/vector_join_nulls.q.out @@ -28,7 +28,7 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@myinput1_txt POSTHOOK: Output: database:default POSTHOOK: Output: default@myinput1 -Warning: Map Join MAPJOIN[18][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -38,7 +38,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 13630578 -Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -48,7 +48,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 13630578 -Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git a/ql/src/test/results/clientpositive/vector_left_outer_join.q.out b/ql/src/test/results/clientpositive/vector_left_outer_join.q.out index 2f986c2..13ddc3a 100644 --- a/ql/src/test/results/clientpositive/vector_left_outer_join.q.out +++ b/ql/src/test/results/clientpositive/vector_left_outer_join.q.out @@ -25,72 +25,74 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:c + t1:cd Fetch Operator limit: -1 - $hdt$_0:$hdt$_2:c + t1:hd Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:c + t1:cd TableScan - alias: c + alias: t1:cd Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - $hdt$_0:$hdt$_2:c + 0 cint (type: int) + 1 cint (type: int) + t1:hd TableScan - alias: c + alias: t1:hd Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: c + alias: t1:c Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cint (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 + 0 cint (type: int) + 1 cint (type: int) + outputColumnNames: ctinyint Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) Statistics: Num rows: 14867 Data size: 3196776 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 14867 Data size: 3196776 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -98,15 +100,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_leftsemi_mapjoin.q.out b/ql/src/test/results/clientpositive/vector_leftsemi_mapjoin.q.out index cc8f0c9..087492f 100644 --- a/ql/src/test/results/clientpositive/vector_leftsemi_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/vector_leftsemi_mapjoin.q.out @@ -173,10 +173,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -269,10 +273,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -367,10 +375,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -426,15 +438,19 @@ STAGE PLANS: Filter Operator predicate: (key < 15) (type: boolean) Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: key (type: int), key (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: int) + outputColumnNames: key Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 key (type: int) - 1 _col1 (type: int) + Group By Operator + keys: key (type: int), key (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 key (type: int) + 1 _col1 (type: int) Stage: Stage-2 Map Reduce @@ -558,10 +574,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -842,10 +862,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -937,10 +961,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1046,10 +1074,14 @@ STAGE PLANS: 1 (2 * _col0) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1269,10 +1301,14 @@ STAGE PLANS: 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1400,10 +1436,14 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 24 Data size: 2250 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 24 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 24 Data size: 2250 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1515,10 +1555,14 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1635,12 +1679,16 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -1774,10 +1822,14 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -1904,10 +1956,14 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -2029,12 +2085,16 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -2191,10 +2251,14 @@ STAGE PLANS: 1 value (type: string) outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 1237 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 1237 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 13 Data size: 1237 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -2276,11 +2340,11 @@ STAGE PLANS: Stage: Stage-4 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:b + b Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:b + b TableScan alias: b Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE @@ -2289,17 +2353,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) + HashTable Sink Operator + keys: + 0 value (type: string) + 1 value (type: string) Stage: Stage-3 Map Reduce @@ -2308,27 +2367,31 @@ STAGE PLANS: alias: a Statistics: Num rows: 22 Data size: 2046 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > 100) and value is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + predicate: (value is not null and (key > 100)) (type: boolean) + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: int) + outputColumnNames: key Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -2403,10 +2466,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -2499,10 +2566,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -2597,10 +2668,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -2656,15 +2731,19 @@ STAGE PLANS: Filter Operator predicate: (key < 15) (type: boolean) Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: key (type: int), key (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: int) + outputColumnNames: key Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 key (type: int) - 1 _col1 (type: int) + Group By Operator + keys: key (type: int), key (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 key (type: int) + 1 _col1 (type: int) Stage: Stage-2 Map Reduce @@ -2788,10 +2867,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -3072,10 +3155,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -3167,10 +3254,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -3276,10 +3367,14 @@ STAGE PLANS: 1 (2 * _col0) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -3499,10 +3594,14 @@ STAGE PLANS: 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -3630,10 +3729,14 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 24 Data size: 2250 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 24 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 24 Data size: 2250 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -3745,10 +3848,14 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -3865,12 +3972,16 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -4004,10 +4115,14 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -4134,10 +4249,14 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -4259,12 +4378,16 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -4421,10 +4544,14 @@ STAGE PLANS: 1 value (type: string) outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 1237 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 1237 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 13 Data size: 1237 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -4506,11 +4633,11 @@ STAGE PLANS: Stage: Stage-4 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:b + b Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:b + b TableScan alias: b Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE @@ -4519,17 +4646,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) + HashTable Sink Operator + keys: + 0 value (type: string) + 1 value (type: string) Stage: Stage-3 Map Reduce @@ -4538,27 +4660,31 @@ STAGE PLANS: alias: a Statistics: Num rows: 22 Data size: 2046 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > 100) and value is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + predicate: (value is not null and (key > 100)) (type: boolean) + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: int) + outputColumnNames: key Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -4633,10 +4759,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -4730,10 +4860,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -4829,10 +4963,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -4889,15 +5027,19 @@ STAGE PLANS: Filter Operator predicate: (key < 15) (type: boolean) Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: key (type: int), key (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: int) + outputColumnNames: key Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 key (type: int) - 1 _col1 (type: int) + Group By Operator + keys: key (type: int), key (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 key (type: int) + 1 _col1 (type: int) Stage: Stage-2 Map Reduce @@ -5022,10 +5164,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -5309,10 +5455,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -5405,10 +5555,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -5515,10 +5669,14 @@ STAGE PLANS: 1 (2 * _col0) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -5740,10 +5898,14 @@ STAGE PLANS: 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -5872,10 +6034,14 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 24 Data size: 2250 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 24 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 24 Data size: 2250 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -5988,10 +6154,14 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -6109,12 +6279,16 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -6248,10 +6422,14 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -6379,10 +6557,14 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -6505,12 +6687,16 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -6667,10 +6853,14 @@ STAGE PLANS: 1 value (type: string) outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 1237 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 1237 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 13 Data size: 1237 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -6753,11 +6943,11 @@ STAGE PLANS: Stage: Stage-4 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:b + b Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:b + b TableScan alias: b Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE @@ -6766,17 +6956,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) + HashTable Sink Operator + keys: + 0 value (type: string) + 1 value (type: string) Stage: Stage-3 Map Reduce @@ -6785,27 +6970,31 @@ STAGE PLANS: alias: a Statistics: Num rows: 22 Data size: 2046 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > 100) and value is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + predicate: (value is not null and (key > 100)) (type: boolean) + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: int) + outputColumnNames: key Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work Execution mode: vectorized @@ -6881,10 +7070,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -6978,10 +7171,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -7077,10 +7274,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -7137,15 +7338,19 @@ STAGE PLANS: Filter Operator predicate: (key < 15) (type: boolean) Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: key (type: int), key (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: int) + outputColumnNames: key Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 key (type: int) - 1 _col1 (type: int) + Group By Operator + keys: key (type: int), key (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 key (type: int) + 1 _col1 (type: int) Stage: Stage-2 Map Reduce @@ -7270,10 +7475,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -7557,10 +7766,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -7653,10 +7866,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -7763,10 +7980,14 @@ STAGE PLANS: 1 (2 * _col0) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -7988,10 +8209,14 @@ STAGE PLANS: 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -8120,10 +8345,14 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 24 Data size: 2250 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 24 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 24 Data size: 2250 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -8236,10 +8465,14 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -8357,12 +8590,16 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -8496,10 +8733,14 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -8627,10 +8868,14 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -8753,12 +8998,16 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -8915,10 +9164,14 @@ STAGE PLANS: 1 value (type: string) outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 1237 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 1237 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 13 Data size: 1237 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -9001,11 +9254,11 @@ STAGE PLANS: Stage: Stage-4 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:b + b Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:b + b TableScan alias: b Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE @@ -9014,17 +9267,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) + HashTable Sink Operator + keys: + 0 value (type: string) + 1 value (type: string) Stage: Stage-3 Map Reduce @@ -9033,27 +9281,31 @@ STAGE PLANS: alias: a Statistics: Num rows: 22 Data size: 2046 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > 100) and value is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + predicate: (value is not null and (key > 100)) (type: boolean) + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Semi Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + keys: + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: int) + outputColumnNames: key Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work Execution mode: vectorized @@ -9129,10 +9381,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -9226,10 +9482,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -9325,10 +9585,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -9385,15 +9649,19 @@ STAGE PLANS: Filter Operator predicate: (key < 15) (type: boolean) Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: key (type: int), key (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: int) + outputColumnNames: key Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 key (type: int) - 1 _col1 (type: int) + Group By Operator + keys: key (type: int), key (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 key (type: int) + 1 _col1 (type: int) Stage: Stage-2 Map Reduce @@ -9518,10 +9786,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -9805,10 +10077,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -9901,10 +10177,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -10011,10 +10291,14 @@ STAGE PLANS: 1 (2 * _col0) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -10236,10 +10520,14 @@ STAGE PLANS: 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -10368,10 +10656,14 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 24 Data size: 2250 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 24 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 24 Data size: 2250 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -10484,10 +10776,14 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -10605,12 +10901,16 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -10744,10 +11044,14 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -10875,10 +11179,14 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -11001,12 +11309,16 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -11163,10 +11475,14 @@ STAGE PLANS: 1 value (type: string) outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 1237 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 1237 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 13 Data size: 1237 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -11249,11 +11565,11 @@ STAGE PLANS: Stage: Stage-4 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:b + b Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:b + b TableScan alias: b Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE @@ -11262,17 +11578,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) + HashTable Sink Operator + keys: + 0 value (type: string) + 1 value (type: string) Stage: Stage-3 Map Reduce @@ -11281,27 +11592,31 @@ STAGE PLANS: alias: a Statistics: Num rows: 22 Data size: 2046 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > 100) and value is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + predicate: (value is not null and (key > 100)) (type: boolean) + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: int) + outputColumnNames: key Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work Execution mode: vectorized @@ -11377,10 +11692,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -11474,10 +11793,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -11573,10 +11896,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -11633,15 +11960,19 @@ STAGE PLANS: Filter Operator predicate: (key < 15) (type: boolean) Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: key (type: int), key (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: int) + outputColumnNames: key Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 key (type: int) - 1 _col1 (type: int) + Group By Operator + keys: key (type: int), key (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 key (type: int) + 1 _col1 (type: int) Stage: Stage-2 Map Reduce @@ -11766,10 +12097,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -12053,10 +12388,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -12149,10 +12488,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -12259,10 +12602,14 @@ STAGE PLANS: 1 (2 * _col0) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -12484,10 +12831,14 @@ STAGE PLANS: 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -12616,10 +12967,14 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 24 Data size: 2250 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 24 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 24 Data size: 2250 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -12732,10 +13087,14 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -12853,12 +13212,16 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -12992,10 +13355,14 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -13123,10 +13490,14 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -13249,12 +13620,16 @@ STAGE PLANS: 2 key (type: int) outputColumnNames: _col0 Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 48 Data size: 4501 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -13411,10 +13786,14 @@ STAGE PLANS: 1 value (type: string) outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 1237 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 1237 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 13 Data size: 1237 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Execution mode: vectorized @@ -13497,11 +13876,11 @@ STAGE PLANS: Stage: Stage-4 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:b + b Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:b + b TableScan alias: b Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE @@ -13510,17 +13889,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) + HashTable Sink Operator + keys: + 0 value (type: string) + 1 value (type: string) Stage: Stage-3 Map Reduce @@ -13529,27 +13903,31 @@ STAGE PLANS: alias: a Statistics: Num rows: 22 Data size: 2046 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key > 100) and value is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + predicate: (value is not null and (key > 100)) (type: boolean) + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: key, value + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 value (type: string) + 1 value (type: string) + outputColumnNames: key Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: key (type: int) + outputColumnNames: key Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work Execution mode: vectorized diff --git a/ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out b/ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out index fdd7ea8..7318372 100644 --- a/ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out +++ b/ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out @@ -39,17 +39,17 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: lineitem + alias: p:lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_partkey (type: int) - outputColumnNames: _col0 + outputColumnNames: l_partkey Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: l_partkey (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE @@ -62,7 +62,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: l_partkey Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -85,8 +85,8 @@ STAGE PLANS: TableScan HashTable Sink Operator keys: - 0 _col1 (type: int) - 1 _col0 (type: int) + 0 l_partkey (type: int) + 1 l_partkey (type: int) Stage: Stage-5 Map Reduce @@ -96,13 +96,13 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 + 0 l_partkey (type: int) + 1 l_partkey (type: int) + outputColumnNames: l_partkey, l_suppkey Statistics: Num rows: 29 Data size: 3627 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int), _col2 (type: int) - outputColumnNames: _col0, _col1 + expressions: l_partkey (type: int), l_suppkey (type: int) + outputColumnNames: p_partkey, l_suppkey Statistics: Num rows: 29 Data size: 3627 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -125,8 +125,8 @@ STAGE PLANS: TableScan HashTable Sink Operator keys: - 0 _col1 (type: int) - 1 _col0 (type: int) + 0 l_partkey (type: int) + 1 l_partkey (type: int) Stage: Stage-6 Map Reduce @@ -136,13 +136,13 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 + 0 l_partkey (type: int) + 1 l_partkey (type: int) + outputColumnNames: l_partkey, l_suppkey Statistics: Num rows: 29 Data size: 3627 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int), _col2 (type: int) - outputColumnNames: _col0, _col1 + expressions: l_partkey (type: int), l_suppkey (type: int) + outputColumnNames: p_partkey, l_suppkey Statistics: Num rows: 29 Data size: 3627 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -159,29 +159,29 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col1 (type: int) + key expressions: l_partkey (type: int) sort order: + - Map-reduce partition columns: _col1 (type: int) + Map-reduce partition columns: l_partkey (type: int) Statistics: Num rows: 27 Data size: 3298 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int) + value expressions: l_suppkey (type: int) TableScan Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: l_partkey (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: l_partkey (type: int) Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 + 0 l_partkey (type: int) + 1 l_partkey (type: int) + outputColumnNames: l_partkey, l_suppkey Statistics: Num rows: 29 Data size: 3627 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int), _col2 (type: int) - outputColumnNames: _col0, _col1 + expressions: l_partkey (type: int), l_suppkey (type: int) + outputColumnNames: p_partkey, l_suppkey Statistics: Num rows: 29 Data size: 3627 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -194,51 +194,46 @@ STAGE PLANS: Stage: Stage-11 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:lineitem + sq_1:lineitem Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:lineitem + sq_1:lineitem TableScan - alias: lineitem + alias: sq_1:lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((l_shipmode = 'AIR') and l_orderkey is not null) (type: boolean) Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int) - outputColumnNames: _col0 + outputColumnNames: l_orderkey Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + HashTable Sink Operator + keys: + 0 l_orderkey (type: int) + 1 l_orderkey (type: int) Stage: Stage-8 Map Reduce Map Operator Tree: TableScan - alias: lineitem + alias: li Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((l_linenumber = 1) and l_orderkey is not null) and l_partkey is not null) (type: boolean) - Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE + predicate: ((l_orderkey is not null and l_partkey is not null) and (l_linenumber = 1)) (type: boolean) + Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: l_orderkey, l_partkey, l_suppkey + Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 + 0 l_orderkey (type: int) + 1 l_orderkey (type: int) + outputColumnNames: l_partkey, l_suppkey Statistics: Num rows: 27 Data size: 3298 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -310,17 +305,17 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: lineitem + alias: p:lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_partkey (type: int) - outputColumnNames: _col0 + outputColumnNames: l_partkey Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: l_partkey (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE @@ -333,7 +328,7 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: l_partkey Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -356,8 +351,8 @@ STAGE PLANS: TableScan HashTable Sink Operator keys: - 0 _col1 (type: int) - 1 _col0 (type: int) + 0 l_partkey (type: int) + 1 l_partkey (type: int) Stage: Stage-5 Map Reduce @@ -367,13 +362,13 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 + 0 l_partkey (type: int) + 1 l_partkey (type: int) + outputColumnNames: l_partkey, l_suppkey Statistics: Num rows: 27 Data size: 3298 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int), _col2 (type: int) - outputColumnNames: _col0, _col1 + expressions: l_partkey (type: int), l_suppkey (type: int) + outputColumnNames: p_partkey, l_suppkey Statistics: Num rows: 27 Data size: 3298 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -396,8 +391,8 @@ STAGE PLANS: TableScan HashTable Sink Operator keys: - 0 _col1 (type: int) - 1 _col0 (type: int) + 0 l_partkey (type: int) + 1 l_partkey (type: int) Stage: Stage-6 Map Reduce @@ -407,13 +402,13 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 + 0 l_partkey (type: int) + 1 l_partkey (type: int) + outputColumnNames: l_partkey, l_suppkey Statistics: Num rows: 27 Data size: 3298 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int), _col2 (type: int) - outputColumnNames: _col0, _col1 + expressions: l_partkey (type: int), l_suppkey (type: int) + outputColumnNames: p_partkey, l_suppkey Statistics: Num rows: 27 Data size: 3298 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -430,29 +425,29 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col1 (type: int) + key expressions: l_partkey (type: int) sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 14 Data size: 1714 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int) + Map-reduce partition columns: l_partkey (type: int) + Statistics: Num rows: 6 Data size: 790 Basic stats: COMPLETE Column stats: NONE + value expressions: l_suppkey (type: int) TableScan Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: l_partkey (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: l_partkey (type: int) Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 + 0 l_partkey (type: int) + 1 l_partkey (type: int) + outputColumnNames: l_partkey, l_suppkey Statistics: Num rows: 27 Data size: 3298 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int), _col2 (type: int) - outputColumnNames: _col0, _col1 + expressions: l_partkey (type: int), l_suppkey (type: int) + outputColumnNames: p_partkey, l_suppkey Statistics: Num rows: 27 Data size: 3298 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -465,52 +460,47 @@ STAGE PLANS: Stage: Stage-11 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:$hdt$_1:lineitem + sq_1:lineitem Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:$hdt$_1:lineitem + sq_1:lineitem TableScan - alias: lineitem + alias: sq_1:lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((l_shipmode = 'AIR') and (l_linenumber = 1)) and l_orderkey is not null) (type: boolean) - Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE + predicate: ((((l_shipmode = 'AIR') and l_linenumber is not null) and l_orderkey is not null) and (l_linenumber = 1)) (type: boolean) + Statistics: Num rows: 6 Data size: 719 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + outputColumnNames: l_orderkey + Statistics: Num rows: 6 Data size: 719 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 l_orderkey (type: int) + 1 l_orderkey (type: int) Stage: Stage-8 Map Reduce Map Operator Tree: TableScan - alias: lineitem + alias: li Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((l_linenumber = 1) and l_orderkey is not null) and l_partkey is not null) (type: boolean) - Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE + predicate: (((l_linenumber is not null and l_orderkey is not null) and l_partkey is not null) and (l_linenumber = 1)) (type: boolean) + Statistics: Num rows: 6 Data size: 719 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 1559 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: l_orderkey, l_partkey, l_suppkey + Statistics: Num rows: 6 Data size: 719 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Semi Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 14 Data size: 1714 Basic stats: COMPLETE Column stats: NONE + 0 l_orderkey (type: int) + 1 l_orderkey (type: int) + outputColumnNames: l_partkey, l_suppkey + Statistics: Num rows: 6 Data size: 790 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/vector_mr_diff_schema_alias.q.out b/ql/src/test/results/clientpositive/vector_mr_diff_schema_alias.q.out index 288025d..9e11a78 100644 --- a/ql/src/test/results/clientpositive/vector_mr_diff_schema_alias.q.out +++ b/ql/src/test/results/clientpositive/vector_mr_diff_schema_alias.q.out @@ -356,12 +356,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce diff --git a/ql/src/test/results/clientpositive/vector_non_string_partition.q.out b/ql/src/test/results/clientpositive/vector_non_string_partition.q.out index bf2e432..a1b6464 100644 --- a/ql/src/test/results/clientpositive/vector_non_string_partition.q.out +++ b/ql/src/test/results/clientpositive/vector_non_string_partition.q.out @@ -47,18 +47,18 @@ STAGE PLANS: Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1 + outputColumnNames: cint, ctinyint Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: cint (type: int) sort order: + Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: tinyint) + value expressions: ctinyint (type: tinyint) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: tinyint) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: int), VALUE.ctinyint (type: tinyint) + outputColumnNames: cint, ctinyint Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -117,17 +117,17 @@ STAGE PLANS: Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cstring1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: cint, cstring1 Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) + key expressions: cint (type: int), cstring1 (type: string) sort order: ++ Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: cint, cstring1 Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 diff --git a/ql/src/test/results/clientpositive/vector_null_projection.q.out b/ql/src/test/results/clientpositive/vector_null_projection.q.out index b3b44ad..6043baf 100644 --- a/ql/src/test/results/clientpositive/vector_null_projection.q.out +++ b/ql/src/test/results/clientpositive/vector_null_projection.q.out @@ -57,7 +57,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: null (type: void) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE File Output Operator compressed: false @@ -97,18 +97,20 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a + alias: _u2-subquery1:_u1-subquery1:a Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: null (type: void) - outputColumnNames: _col0 + outputColumnNames: x Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Union Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator + expressions: null (type: void) + outputColumnNames: $f0 Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Group By Operator - keys: null (type: void) + keys: $f0 (type: void) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE @@ -118,18 +120,20 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: void) Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE TableScan - alias: b + alias: _u2-subquery2:_u1-subquery2:b Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: null (type: void) - outputColumnNames: _col0 + outputColumnNames: x Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Union Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Select Operator + expressions: null (type: void) + outputColumnNames: $f0 Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Group By Operator - keys: null (type: void) + keys: $f0 (type: void) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE @@ -142,15 +146,19 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: void) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: void) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_orderby_5.q.out b/ql/src/test/results/clientpositive/vector_orderby_5.q.out index 45ccc62..a5d5908 100644 --- a/ql/src/test/results/clientpositive/vector_orderby_5.q.out +++ b/ql/src/test/results/clientpositive/vector_orderby_5.q.out @@ -121,11 +121,11 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: bo (type: boolean), b (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: boolean) + aggregations: max($f1) + keys: $f0 (type: boolean) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE @@ -141,28 +141,32 @@ STAGE PLANS: aggregations: max(VALUE._col0) keys: KEY._col0 (type: boolean) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: boolean), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: boolean) + key expressions: $f0 (type: boolean) sort order: - Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: $f1 (type: bigint) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: boolean), VALUE._col0 (type: bigint) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: boolean), VALUE.$f1 (type: bigint) + outputColumnNames: $f0, $f1 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vector_outer_join1.q.out b/ql/src/test/results/clientpositive/vector_outer_join1.q.out index 8e8f7fa..6d158e8 100644 --- a/ql/src/test/results/clientpositive/vector_outer_join1.q.out +++ b/ql/src/test/results/clientpositive/vector_outer_join1.q.out @@ -177,22 +177,22 @@ STAGE PLANS: Stage: Stage-4 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:c + cd Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:c + cd TableScan - alias: c + alias: cd Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + outputColumnNames: ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col2 (type: int) - 1 _col2 (type: int) + 0 cint (type: int) + 1 cint (type: int) Stage: Stage-3 Map Reduce @@ -202,23 +202,27 @@ STAGE PLANS: Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + outputColumnNames: ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col2 (type: int) - 1 _col2 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 + 0 cint (type: int) + 1 cint (type: int) + outputColumnNames: ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2, ctinyint0, csmallint0, cint0, cbigint0, cfloat0, cdouble0, cstring10, cstring20, ctimestamp10, ctimestamp20, cboolean10, cboolean20 Statistics: Num rows: 16 Data size: 3652 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean), ctinyint0 (type: tinyint), csmallint0 (type: smallint), cint0 (type: int), cbigint0 (type: bigint), cfloat0 (type: float), cdouble0 (type: double), cstring10 (type: string), cstring20 (type: string), ctimestamp10 (type: timestamp), ctimestamp20 (type: timestamp), cboolean10 (type: boolean), cboolean20 (type: boolean) + outputColumnNames: ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2, ctinyint0, csmallint0, cint0, cbigint0, cfloat0, cdouble0, cstring10, cstring20, ctimestamp10, ctimestamp20, cboolean10, cboolean20 Statistics: Num rows: 16 Data size: 3652 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 16 Data size: 3652 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work Execution mode: vectorized @@ -287,22 +291,22 @@ STAGE PLANS: Stage: Stage-4 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:c + hd Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:c + hd TableScan - alias: c + alias: hd Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) Stage: Stage-3 Map Reduce @@ -312,23 +316,27 @@ STAGE PLANS: Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) - outputColumnNames: _col0 + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) + outputColumnNames: ctinyint Statistics: Num rows: 16 Data size: 3652 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: ctinyint Statistics: Num rows: 16 Data size: 3652 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 16 Data size: 3652 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work Execution mode: vectorized @@ -489,73 +497,77 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:c + t1:cd Fetch Operator limit: -1 - $hdt$_0:$hdt$_2:c + t1:hd Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:c + t1:cd TableScan - alias: c + alias: t1:cd Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - $hdt$_0:$hdt$_2:c + 0 cint (type: int) + 1 cint (type: int) + t1:hd TableScan - alias: c + alias: t1:hd Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: c + alias: t1:c Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cint (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cint Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 + 0 cint (type: int) + 1 cint (type: int) + outputColumnNames: ctinyint Statistics: Num rows: 16 Data size: 3652 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) - outputColumnNames: _col0 + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) + outputColumnNames: ctinyint Statistics: Num rows: 17 Data size: 4017 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(), sum(_col0) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: c_ctinyint + Statistics: Num rows: 17 Data size: 4017 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(), sum(c_ctinyint) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -563,15 +575,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_outer_join2.q.out b/ql/src/test/results/clientpositive/vector_outer_join2.q.out index c649883..6e86602 100644 --- a/ql/src/test/results/clientpositive/vector_outer_join2.q.out +++ b/ql/src/test/results/clientpositive/vector_outer_join2.q.out @@ -193,70 +193,70 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:c + t1:cd Fetch Operator limit: -1 - $hdt$_0:$hdt$_2:c + t1:hd Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:c + t1:cd TableScan - alias: c + alias: t1:cd Statistics: Num rows: 20 Data size: 4182 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 20 Data size: 4182 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - $hdt$_0:$hdt$_2:c + 0 cint (type: int) + 1 cint (type: int) + t1:hd TableScan - alias: c + alias: t1:hd Statistics: Num rows: 20 Data size: 4182 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) - outputColumnNames: _col0 + outputColumnNames: cbigint Statistics: Num rows: 20 Data size: 4182 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col1 (type: bigint) - 1 _col0 (type: bigint) + 0 cbigint (type: bigint) + 1 cbigint (type: bigint) Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: c + alias: t1:c Statistics: Num rows: 20 Data size: 4182 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cbigint (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: cint, cbigint Statistics: Num rows: 20 Data size: 4182 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 + 0 cint (type: int) + 1 cint (type: int) + outputColumnNames: cbigint Statistics: Num rows: 22 Data size: 4600 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col1 (type: bigint) - 1 _col0 (type: bigint) - outputColumnNames: _col1 + 0 cbigint (type: bigint) + 1 cbigint (type: bigint) + outputColumnNames: cbigint Statistics: Num rows: 24 Data size: 5060 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 + expressions: cbigint (type: bigint) + outputColumnNames: c_cbigint Statistics: Num rows: 24 Data size: 5060 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), sum(_col0) + aggregations: count(), sum(c_cbigint) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -271,15 +271,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0), sum(VALUE._col1) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_outer_join3.q.out b/ql/src/test/results/clientpositive/vector_outer_join3.q.out index 502f2d3..ef0e84c 100644 --- a/ql/src/test/results/clientpositive/vector_outer_join3.q.out +++ b/ql/src/test/results/clientpositive/vector_outer_join3.q.out @@ -193,72 +193,74 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:c + t1:cd Fetch Operator limit: -1 - $hdt$_0:$hdt$_2:c + t1:hd Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:c + t1:cd TableScan - alias: c + alias: t1:cd Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - $hdt$_0:$hdt$_2:c + 0 cint (type: int) + 1 cint (type: int) + t1:hd TableScan - alias: c + alias: t1:hd Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string) - outputColumnNames: _col0 + outputColumnNames: cstring1 Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col1 (type: string) - 1 _col0 (type: string) + 0 cstring1 (type: string) + 1 cstring1 (type: string) Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: c + alias: t1:c Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cstring1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: cint, cstring1 Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 + 0 cint (type: int) + 1 cint (type: int) + outputColumnNames: cstring1 Statistics: Num rows: 22 Data size: 4840 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) + 0 cstring1 (type: string) + 1 cstring1 (type: string) Statistics: Num rows: 24 Data size: 5324 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 24 Data size: 5324 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -266,15 +268,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -334,72 +340,74 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:c + t1:cd Fetch Operator limit: -1 - $hdt$_0:$hdt$_2:c + t1:hd Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:c + t1:cd TableScan - alias: c + alias: t1:cd Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring2 (type: string) - outputColumnNames: _col0 + outputColumnNames: cstring2 Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - $hdt$_0:$hdt$_2:c + 0 cstring2 (type: string) + 1 cstring2 (type: string) + t1:hd TableScan - alias: c + alias: t1:hd Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string) - outputColumnNames: _col0 + outputColumnNames: cstring1 Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 cstring1 (type: string) + 1 cstring1 (type: string) Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: c + alias: t1:c Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string), cstring2 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: cstring1, cstring2 Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 + 0 cstring2 (type: string) + 1 cstring2 (type: string) + outputColumnNames: cstring1 Statistics: Num rows: 22 Data size: 4840 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 cstring1 (type: string) + 1 cstring1 (type: string) Statistics: Num rows: 24 Data size: 5324 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 24 Data size: 5324 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -407,15 +415,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -475,72 +487,74 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:c + t1:cd Fetch Operator limit: -1 - $hdt$_0:$hdt$_2:c + t1:hd Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:c + t1:cd TableScan - alias: c + alias: t1:cd Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cstring2 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: cbigint, cstring2 Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col3 (type: string), _col1 (type: bigint) - 1 _col1 (type: string), _col0 (type: bigint) - $hdt$_0:$hdt$_2:c + 0 cstring2 (type: string), cbigint (type: bigint) + 1 cstring2 (type: string), cbigint (type: bigint) + t1:hd TableScan - alias: c + alias: t1:hd Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cstring1 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: cint, cstring1 Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col2 (type: string), _col0 (type: int) - 1 _col1 (type: string), _col0 (type: int) + 0 cstring1 (type: string), cint (type: int) + 1 cstring1 (type: string), cint (type: int) Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: c + alias: t1:c Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cbigint (type: bigint), cstring1 (type: string), cstring2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: cint, cbigint, cstring1, cstring2 Statistics: Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col3 (type: string), _col1 (type: bigint) - 1 _col1 (type: string), _col0 (type: bigint) - outputColumnNames: _col0, _col2 + 0 cstring2 (type: string), cbigint (type: bigint) + 1 cstring2 (type: string), cbigint (type: bigint) + outputColumnNames: cint, cstring1 Statistics: Num rows: 22 Data size: 4840 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col2 (type: string), _col0 (type: int) - 1 _col1 (type: string), _col0 (type: int) + 0 cstring1 (type: string), cint (type: int) + 1 cstring1 (type: string), cint (type: int) Statistics: Num rows: 24 Data size: 5324 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 24 Data size: 5324 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -548,15 +562,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_outer_join4.q.out b/ql/src/test/results/clientpositive/vector_outer_join4.q.out index 50ae497..92eaa9e 100644 --- a/ql/src/test/results/clientpositive/vector_outer_join4.q.out +++ b/ql/src/test/results/clientpositive/vector_outer_join4.q.out @@ -207,22 +207,22 @@ STAGE PLANS: Stage: Stage-4 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:c + cd Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:c + cd TableScan - alias: c + alias: cd Statistics: Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + outputColumnNames: ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 Statistics: Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col2 (type: int) - 1 _col2 (type: int) + 0 cint (type: int) + 1 cint (type: int) Stage: Stage-3 Map Reduce @@ -232,23 +232,27 @@ STAGE PLANS: Statistics: Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + outputColumnNames: ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 Statistics: Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col2 (type: int) - 1 _col2 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 + 0 cint (type: int) + 1 cint (type: int) + outputColumnNames: ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2, ctinyint0, csmallint0, cint0, cbigint0, cfloat0, cdouble0, cstring10, cstring20, ctimestamp10, ctimestamp20, cboolean10, cboolean20 Statistics: Num rows: 33 Data size: 7348 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean), ctinyint0 (type: tinyint), csmallint0 (type: smallint), cint0 (type: int), cbigint0 (type: bigint), cfloat0 (type: float), cdouble0 (type: double), cstring10 (type: string), cstring20 (type: string), ctimestamp10 (type: timestamp), ctimestamp20 (type: timestamp), cboolean10 (type: boolean), cboolean20 (type: boolean) + outputColumnNames: ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2, ctinyint0, csmallint0, cint0, cbigint0, cfloat0, cdouble0, cstring10, cstring20, ctimestamp10, ctimestamp20, cboolean10, cboolean20 Statistics: Num rows: 33 Data size: 7348 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 33 Data size: 7348 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work Execution mode: vectorized @@ -352,22 +356,22 @@ STAGE PLANS: Stage: Stage-4 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:c + hd Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:c + hd TableScan - alias: c + alias: hd Statistics: Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) Stage: Stage-3 Map Reduce @@ -377,23 +381,27 @@ STAGE PLANS: Statistics: Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) - outputColumnNames: _col0 + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) + outputColumnNames: ctinyint Statistics: Num rows: 33 Data size: 7348 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: ctinyint Statistics: Num rows: 33 Data size: 7348 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 33 Data size: 7348 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work Execution mode: vectorized @@ -859,72 +867,74 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:c + t1:cd Fetch Operator limit: -1 - $hdt$_0:$hdt$_2:c + t1:hd Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:c + t1:cd TableScan - alias: c + alias: t1:cd Statistics: Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - $hdt$_0:$hdt$_2:c + 0 cint (type: int) + 1 cint (type: int) + t1:hd TableScan - alias: c + alias: t1:hd Statistics: Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: c + alias: t1:c Statistics: Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cint (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cint Statistics: Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 + 0 cint (type: int) + 1 cint (type: int) + outputColumnNames: ctinyint Statistics: Num rows: 33 Data size: 7348 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) Statistics: Num rows: 36 Data size: 8082 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 36 Data size: 8082 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -932,15 +942,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_outer_join5.q.out b/ql/src/test/results/clientpositive/vector_outer_join5.q.out index bbe8ba1..27f078d 100644 --- a/ql/src/test/results/clientpositive/vector_outer_join5.q.out +++ b/ql/src/test/results/clientpositive/vector_outer_join5.q.out @@ -85,49 +85,51 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:st + t1:st Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:st + t1:st TableScan - alias: st + alias: t1:st Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: s + alias: t1:s Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -135,15 +137,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -193,55 +199,57 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:sm + t1:sm Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:sm + t1:sm TableScan - alias: sm + alias: t1:sm Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator filter predicates: - 0 {(_col1 = 2)} + 0 {(cmodint = 2)} 1 keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: s + alias: t1:s Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cmodint (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cmodint Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 filter predicates: - 0 {(_col1 = 2)} + 0 {(cmodint = 2)} 1 keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -249,15 +257,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -307,55 +319,57 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:sm + t1:sm Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:sm + t1:sm TableScan - alias: sm + alias: t1:sm Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator filter predicates: - 0 {((UDFToInteger(_col0) pmod 4) = _col1)} + 0 {((UDFToInteger(ctinyint) pmod 4) = cmodint)} 1 keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: s + alias: t1:s Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cmodint (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cmodint Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 filter predicates: - 0 {((UDFToInteger(_col0) pmod 4) = _col1)} + 0 {((UDFToInteger(ctinyint) pmod 4) = cmodint)} 1 keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -363,15 +377,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -421,55 +439,57 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:sm + t1:sm Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:sm + t1:sm TableScan - alias: sm + alias: t1:sm Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator filter predicates: - 0 {(_col0 < 100)} + 0 {(ctinyint < 100)} 1 keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: s + alias: t1:s Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 filter predicates: - 0 {(_col0 < 100)} + 0 {(ctinyint < 100)} 1 keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -477,15 +497,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -539,72 +563,74 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:sm + t1:s2 Fetch Operator limit: -1 - $hdt$_0:$hdt$_2:s + t1:sm Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:sm + t1:s2 TableScan - alias: sm - Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE + alias: t1:s2 + Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cbigint (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE + expressions: ctinyint (type: tinyint) + outputColumnNames: ctinyint + Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 UDFToLong(_col1) (type: bigint) - 1 (_col0 pmod UDFToLong(8)) (type: bigint) - $hdt$_0:$hdt$_2:s + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) + t1:sm TableScan - alias: s - Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE + alias: t1:sm + Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 - Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE + expressions: cbigint (type: bigint) + outputColumnNames: cbigint + Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + 0 UDFToLong(cmodint) (type: bigint) + 1 (cbigint pmod UDFToLong(8)) (type: bigint) Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: s + alias: t1:s Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cmodint (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cmodint Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 UDFToLong(_col1) (type: bigint) - 1 (_col0 pmod UDFToLong(8)) (type: bigint) - outputColumnNames: _col0 + 0 UDFToLong(cmodint) (type: bigint) + 1 (cbigint pmod UDFToLong(8)) (type: bigint) + outputColumnNames: ctinyint Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) Statistics: Num rows: 7329 Data size: 58641 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 7329 Data size: 58641 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -612,15 +638,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -732,49 +762,51 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:st + t1:st Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:st + t1:st TableScan - alias: st + alias: t1:st Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cmodtinyint (type: int) - outputColumnNames: _col0 + outputColumnNames: cmodtinyint Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 cmodtinyint (type: int) + 1 cmodtinyint (type: int) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: s + alias: t1:s Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cmodtinyint (type: int) - outputColumnNames: _col0 + outputColumnNames: cmodtinyint Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 cmodtinyint (type: int) + 1 cmodtinyint (type: int) Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -782,15 +814,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -840,55 +876,57 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:sm + t1:sm Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:sm + t1:sm TableScan - alias: sm + alias: t1:sm Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cmodtinyint (type: int) - outputColumnNames: _col0 + outputColumnNames: cmodtinyint Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator filter predicates: - 0 {(_col1 = 2)} + 0 {(cmodint = 2)} 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 cmodtinyint (type: int) + 1 cmodtinyint (type: int) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: s + alias: t1:s Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cmodtinyint (type: int), cmodint (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: cmodtinyint, cmodint Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 filter predicates: - 0 {(_col1 = 2)} + 0 {(cmodint = 2)} 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 cmodtinyint (type: int) + 1 cmodtinyint (type: int) Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -896,15 +934,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -954,55 +996,57 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:sm + t1:sm Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:sm + t1:sm TableScan - alias: sm + alias: t1:sm Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cmodtinyint (type: int) - outputColumnNames: _col0 + outputColumnNames: cmodtinyint Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator filter predicates: - 0 {((_col0 pmod 4) = _col1)} + 0 {((cmodtinyint pmod 4) = cmodint)} 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 cmodtinyint (type: int) + 1 cmodtinyint (type: int) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: s + alias: t1:s Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cmodtinyint (type: int), cmodint (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: cmodtinyint, cmodint Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 filter predicates: - 0 {((_col0 pmod 4) = _col1)} + 0 {((cmodtinyint pmod 4) = cmodint)} 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 cmodtinyint (type: int) + 1 cmodtinyint (type: int) Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -1010,15 +1054,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1068,55 +1116,57 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:sm + t1:sm Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:sm + t1:sm TableScan - alias: sm + alias: t1:sm Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cmodtinyint (type: int) - outputColumnNames: _col0 + outputColumnNames: cmodtinyint Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator filter predicates: - 0 {(_col0 < 3)} + 0 {(cmodtinyint < 3)} 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 cmodtinyint (type: int) + 1 cmodtinyint (type: int) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: s + alias: t1:s Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cmodtinyint (type: int) - outputColumnNames: _col0 + outputColumnNames: cmodtinyint Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 filter predicates: - 0 {(_col0 < 3)} + 0 {(cmodtinyint < 3)} 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 cmodtinyint (type: int) + 1 cmodtinyint (type: int) Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -1124,15 +1174,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1186,72 +1240,74 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:sm + t1:s2 Fetch Operator limit: -1 - $hdt$_0:$hdt$_2:s + t1:sm Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:sm + t1:s2 TableScan - alias: sm - Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE + alias: t1:s2 + Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cbigint (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE + expressions: cmodtinyint (type: int) + outputColumnNames: cmodtinyint + Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 UDFToLong(_col1) (type: bigint) - 1 (_col0 pmod UDFToLong(8)) (type: bigint) - $hdt$_0:$hdt$_2:s + 0 cmodtinyint (type: int) + 1 cmodtinyint (type: int) + t1:sm TableScan - alias: s - Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE + alias: t1:sm + Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cmodtinyint (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE + expressions: cbigint (type: bigint) + outputColumnNames: cbigint + Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 UDFToLong(cmodint) (type: bigint) + 1 (cbigint pmod UDFToLong(8)) (type: bigint) Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: s + alias: t1:s Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cmodtinyint (type: int), cmodint (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: cmodtinyint, cmodint Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 UDFToLong(_col1) (type: bigint) - 1 (_col0 pmod UDFToLong(8)) (type: bigint) - outputColumnNames: _col0 + 0 UDFToLong(cmodint) (type: bigint) + 1 (cbigint pmod UDFToLong(8)) (type: bigint) + outputColumnNames: cmodtinyint Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 cmodtinyint (type: int) + 1 cmodtinyint (type: int) Statistics: Num rows: 7329 Data size: 58641 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 7329 Data size: 58641 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Execution mode: vectorized @@ -1259,15 +1315,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_partition_diff_num_cols.q.out b/ql/src/test/results/clientpositive/vector_partition_diff_num_cols.q.out index 0437ff6..e30cdd9 100644 --- a/ql/src/test/results/clientpositive/vector_partition_diff_num_cols.q.out +++ b/ql/src/test/results/clientpositive/vector_partition_diff_num_cols.q.out @@ -95,10 +95,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -111,15 +111,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -214,10 +218,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 11876 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 11876 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -229,15 +233,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -334,10 +342,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -349,15 +357,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -435,10 +447,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -450,15 +462,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -542,10 +558,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -557,15 +573,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_partitioned_date_time.q.out b/ql/src/test/results/clientpositive/vector_partitioned_date_time.q.out index 83e7f19..41b290b 100644 --- a/ql/src/test/results/clientpositive/vector_partitioned_date_time.q.out +++ b/ql/src/test/results/clientpositive/vector_partitioned_date_time.q.out @@ -376,11 +376,11 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_date (type: date) - outputColumnNames: _col0 + outputColumnNames: fl_date Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: date) + keys: fl_date (type: date) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE @@ -396,15 +396,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: date) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: fl_date, $f1 Statistics: Num rows: 68 Data size: 19584 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: fl_date (type: date), $f1 (type: bigint) + outputColumnNames: fl_date, $f1 Statistics: Num rows: 68 Data size: 19584 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 68 Data size: 19584 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -830,7 +834,7 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: origin_city_name (type: string), dest_city_name (type: string), fl_time (type: timestamp), arr_delay (type: float), fl_num (type: int), fl_date (type: date) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: origin_city_name, dest_city_name, fl_time, arr_delay, fl_num, fl_date Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1153,11 +1157,11 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_date (type: date) - outputColumnNames: _col0 + outputColumnNames: fl_date Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: date) + keys: fl_date (type: date) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE @@ -1173,15 +1177,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: date) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: fl_date, $f1 Statistics: Num rows: 68 Data size: 15772 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: fl_date (type: date), $f1 (type: bigint) + outputColumnNames: fl_date, $f1 Statistics: Num rows: 68 Data size: 15772 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 68 Data size: 15772 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1631,7 +1639,7 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: origin_city_name (type: string), dest_city_name (type: string), fl_date (type: date), arr_delay (type: float), fl_num (type: int), fl_time (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: origin_city_name, dest_city_name, fl_date, arr_delay, fl_num, fl_time Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE ListSink @@ -1954,11 +1962,11 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_time (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: fl_time Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: timestamp) + keys: fl_time (type: timestamp) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE @@ -1974,15 +1982,19 @@ STAGE PLANS: aggregations: count(VALUE._col0) keys: KEY._col0 (type: timestamp) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: fl_time, $f1 Statistics: Num rows: 68 Data size: 16860 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: fl_time (type: timestamp), $f1 (type: bigint) + outputColumnNames: fl_time, $f1 Statistics: Num rows: 68 Data size: 16860 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 68 Data size: 16860 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_reduce_groupby_decimal.q.out b/ql/src/test/results/clientpositive/vector_reduce_groupby_decimal.q.out index b38add3..ee93afd 100644 --- a/ql/src/test/results/clientpositive/vector_reduce_groupby_decimal.q.out +++ b/ql/src/test/results/clientpositive/vector_reduce_groupby_decimal.q.out @@ -41,11 +41,11 @@ STAGE PLANS: Statistics: Num rows: 1526 Data size: 360136 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdouble (type: double), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: cint, cdouble, cdecimal1, cdecimal2 Statistics: Num rows: 1526 Data size: 360136 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col2) - keys: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14)) + aggregations: min(cdecimal1) + keys: cint (type: int), cdouble (type: double), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1526 Data size: 360136 Basic stats: COMPLETE Column stats: NONE @@ -61,28 +61,32 @@ STAGE PLANS: aggregations: min(VALUE._col0) keys: KEY._col0 (type: int), KEY._col1 (type: double), KEY._col2 (type: decimal(20,10)), KEY._col3 (type: decimal(23,14)) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: cint, cdouble, cdecimal1, cdecimal2, $f4 Statistics: Num rows: 763 Data size: 180068 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: cint (type: int), cdouble (type: double), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)), $f4 (type: decimal(20,10)) + outputColumnNames: cint, cdouble, cdecimal1, cdecimal2, $f4 + Statistics: Num rows: 763 Data size: 180068 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14)) + key expressions: cint (type: int), cdouble (type: double), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) sort order: ++++ Statistics: Num rows: 763 Data size: 180068 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: decimal(20,10)) + value expressions: $f4 (type: decimal(20,10)) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: decimal(20,10)), KEY.reducesinkkey3 (type: decimal(23,14)), VALUE._col0 (type: decimal(20,10)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: decimal(20,10)), KEY.reducesinkkey3 (type: decimal(23,14)), VALUE.$f4 (type: decimal(20,10)) + outputColumnNames: cint, cdouble, cdecimal1, cdecimal2, $f4 Statistics: Num rows: 763 Data size: 180068 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 50 diff --git a/ql/src/test/results/clientpositive/vector_string_concat.q.out b/ql/src/test/results/clientpositive/vector_string_concat.q.out index 072d837..ba48f4f 100644 --- a/ql/src/test/results/clientpositive/vector_string_concat.q.out +++ b/ql/src/test/results/clientpositive/vector_string_concat.q.out @@ -120,7 +120,7 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s (type: string), concat(concat(' ', s), ' ') (type: string), concat(concat('|', rtrim(concat(concat(' ', s), ' '))), '|') (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: string, none_padded_str, none_z_rtrim_str Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 @@ -309,10 +309,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: concat(concat(concat('Quarter ', UDFToString(UDFToInteger(((UDFToDouble((month(dt) - 1)) / 3.0) + 1.0)))), '-'), UDFToString(year(dt))) (type: string) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: $f0 (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE @@ -326,27 +326,31 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: string) + outputColumnNames: $f0 + Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: $f0 (type: string) sort order: + Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 50 diff --git a/ql/src/test/results/clientpositive/vector_varchar_simple.q.out b/ql/src/test/results/clientpositive/vector_varchar_simple.q.out index 252d45d..d86b672 100644 --- a/ql/src/test/results/clientpositive/vector_varchar_simple.q.out +++ b/ql/src/test/results/clientpositive/vector_varchar_simple.q.out @@ -68,18 +68,18 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: varchar(10)), value (type: varchar(20)) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: varchar(10)) + key expressions: key (type: varchar(10)) sort order: + Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: varchar(20)) + value expressions: value (type: varchar(20)) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: varchar(10)), VALUE._col0 (type: varchar(20)) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: varchar(10)), VALUE.value (type: varchar(20)) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 @@ -161,18 +161,18 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: varchar(10)), value (type: varchar(20)) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: varchar(10)) + key expressions: key (type: varchar(10)) sort order: - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: varchar(20)) + value expressions: value (type: varchar(20)) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: varchar(10)), VALUE._col0 (type: varchar(20)) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: varchar(10)), VALUE.value (type: varchar(20)) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 @@ -242,8 +242,13 @@ insert into table varchar_3 select cint from alltypesorc limit 10 POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 @@ -254,36 +259,33 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: CAST( cint AS varchar(25)) (type: varchar(25)) + outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.varchar_3 Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: CAST( _col0 AS varchar(25)) (type: varchar(25)) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat - serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde - name: default.varchar_3 + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -298,6 +300,26 @@ STAGE PLANS: Stage: Stage-2 Stats-Aggr Operator + Stage: Stage-3 + Merge File Operator + Map Operator Tree: + ORC File Merge Operator + merge level: stripe + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + + Stage: Stage-5 + Merge File Operator + Map Operator Tree: + ORC File Merge Operator + merge level: stripe + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: insert into table varchar_3 select cint from alltypesorc limit 10 PREHOOK: type: QUERY PREHOOK: Input: default@alltypesorc diff --git a/ql/src/test/results/clientpositive/vectorization_0.q.out b/ql/src/test/results/clientpositive/vectorization_0.q.out index 89163cd..3b4703d 100644 --- a/ql/src/test/results/clientpositive/vectorization_0.q.out +++ b/ql/src/test/results/clientpositive/vectorization_0.q.out @@ -50,32 +50,36 @@ STAGE PLANS: Group By Operator aggregations: min(VALUE._col0), max(VALUE._col1), count(VALUE._col2), count(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: tinyint), $f1 (type: tinyint), $f2 (type: bigint), $f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: tinyint) + key expressions: $f0 (type: tinyint) sort order: + - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: tinyint), _col2 (type: bigint), _col3 (type: bigint) + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: tinyint), $f2 (type: bigint), $f3 (type: bigint) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: tinyint), VALUE._col0 (type: tinyint), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + expressions: KEY.reducesinkkey0 (type: tinyint), VALUE.$f1 (type: tinyint), VALUE.$f2 (type: bigint), VALUE.$f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -130,10 +134,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(ctinyint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -146,31 +150,35 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: bigint) + key expressions: $f0 (type: bigint) sort order: + - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -251,28 +259,32 @@ STAGE PLANS: Group By Operator aggregations: avg(VALUE._col0), variance(VALUE._col1), var_pop(VALUE._col2), var_samp(VALUE._col3), std(VALUE._col4), stddev(VALUE._col5), stddev_pop(VALUE._col6), stddev_samp(VALUE._col7) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7 Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: double), $f1 (type: double), $f2 (type: double), $f3 (type: double), $f4 (type: double), $f5 (type: double), $f6 (type: double), $f7 (type: double) + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: double) + key expressions: $f0 (type: double) sort order: + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double) + value expressions: $f1 (type: double), $f2 (type: double), $f3 (type: double), $f4 (type: double), $f5 (type: double), $f6 (type: double), $f7 (type: double) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + expressions: KEY.reducesinkkey0 (type: double), VALUE.$f1 (type: double), VALUE.$f2 (type: double), VALUE.$f3 (type: double), VALUE.$f4 (type: double), VALUE.$f5 (type: double), VALUE.$f6 (type: double), VALUE.$f7 (type: double) + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7 Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -363,32 +375,36 @@ STAGE PLANS: Group By Operator aggregations: min(VALUE._col0), max(VALUE._col1), count(VALUE._col2), count(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: bigint) + key expressions: $f0 (type: bigint) sort order: + - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint) + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: bigint), VALUE._col0 (type: bigint), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + expressions: KEY.reducesinkkey0 (type: bigint), VALUE.$f1 (type: bigint), VALUE.$f2 (type: bigint), VALUE.$f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -443,10 +459,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) - outputColumnNames: _col0 + outputColumnNames: cbigint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(cbigint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -459,31 +475,35 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: bigint) + key expressions: $f0 (type: bigint) sort order: + - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -564,28 +584,32 @@ STAGE PLANS: Group By Operator aggregations: avg(VALUE._col0), variance(VALUE._col1), var_pop(VALUE._col2), var_samp(VALUE._col3), std(VALUE._col4), stddev(VALUE._col5), stddev_pop(VALUE._col6), stddev_samp(VALUE._col7) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7 Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: double), $f1 (type: double), $f2 (type: double), $f3 (type: double), $f4 (type: double), $f5 (type: double), $f6 (type: double), $f7 (type: double) + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: double) + key expressions: $f0 (type: double) sort order: + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double) + value expressions: $f1 (type: double), $f2 (type: double), $f3 (type: double), $f4 (type: double), $f5 (type: double), $f6 (type: double), $f7 (type: double) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + expressions: KEY.reducesinkkey0 (type: double), VALUE.$f1 (type: double), VALUE.$f2 (type: double), VALUE.$f3 (type: double), VALUE.$f4 (type: double), VALUE.$f5 (type: double), VALUE.$f6 (type: double), VALUE.$f7 (type: double) + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7 Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -676,32 +700,36 @@ STAGE PLANS: Group By Operator aggregations: min(VALUE._col0), max(VALUE._col1), count(VALUE._col2), count(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: float), $f1 (type: float), $f2 (type: bigint), $f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: float) + key expressions: $f0 (type: float) sort order: + - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: float), _col2 (type: bigint), _col3 (type: bigint) + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: float), $f2 (type: bigint), $f3 (type: bigint) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: float), VALUE._col0 (type: float), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + expressions: KEY.reducesinkkey0 (type: float), VALUE.$f1 (type: float), VALUE.$f2 (type: bigint), VALUE.$f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -756,10 +784,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) - outputColumnNames: _col0 + outputColumnNames: cfloat Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(cfloat) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -772,31 +800,35 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: double) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: double) + key expressions: $f0 (type: double) sort order: + - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -877,28 +909,32 @@ STAGE PLANS: Group By Operator aggregations: avg(VALUE._col0), variance(VALUE._col1), var_pop(VALUE._col2), var_samp(VALUE._col3), std(VALUE._col4), stddev(VALUE._col5), stddev_pop(VALUE._col6), stddev_samp(VALUE._col7) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7 Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: double), $f1 (type: double), $f2 (type: double), $f3 (type: double), $f4 (type: double), $f5 (type: double), $f6 (type: double), $f7 (type: double) + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: double) + key expressions: $f0 (type: double) sort order: + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double) + value expressions: $f1 (type: double), $f2 (type: double), $f3 (type: double), $f4 (type: double), $f5 (type: double), $f6 (type: double), $f7 (type: double) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + expressions: KEY.reducesinkkey0 (type: double), VALUE.$f1 (type: double), VALUE.$f2 (type: double), VALUE.$f3 (type: double), VALUE.$f4 (type: double), VALUE.$f5 (type: double), VALUE.$f6 (type: double), VALUE.$f7 (type: double) + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7 Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1014,10 +1050,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), stddev_pop(_col0), var_samp(_col0), count(), sum(_col1), min(_col2) + aggregations: avg($f0), stddev_pop($f0), var_samp($f0), count(), sum($f1), min($f2) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE @@ -1030,15 +1066,15 @@ STAGE PLANS: Group By Operator aggregations: avg(VALUE._col0), stddev_pop(VALUE._col1), var_samp(VALUE._col2), count(VALUE._col3), sum(VALUE._col4), min(VALUE._col5) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 44 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), (- _col0) (type: double), (-6432.0 + _col0) (type: double), _col1 (type: double), (- (-6432.0 + _col0)) (type: double), ((- (-6432.0 + _col0)) + (-6432.0 + _col0)) (type: double), _col2 (type: double), (- (-6432.0 + _col0)) (type: double), (-6432.0 + (- (-6432.0 + _col0))) (type: double), (- (-6432.0 + _col0)) (type: double), ((- (-6432.0 + _col0)) / (- (-6432.0 + _col0))) (type: double), _col3 (type: bigint), _col4 (type: double), (_col2 % _col1) (type: double), (- _col2) (type: double), ((- (-6432.0 + _col0)) * (- _col0)) (type: double), _col5 (type: tinyint), (- _col5) (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 1 Data size: 44 Basic stats: COMPLETE Column stats: NONE + expressions: $f0 (type: double), (- $f0) (type: double), (-6432.0 + $f0) (type: double), $f1 (type: double), (- (-6432.0 + $f0)) (type: double), ((- (-6432.0 + $f0)) + (-6432.0 + $f0)) (type: double), $f2 (type: double), (- (-6432.0 + $f0)) (type: double), (-6432.0 + (- (-6432.0 + $f0))) (type: double), (- (-6432.0 + $f0)) (type: double), ((- (-6432.0 + $f0)) / (- (-6432.0 + $f0))) (type: double), $f3 (type: bigint), $f4 (type: double), ($f2 % $f1) (type: double), (- $f2) (type: double), ((- (-6432.0 + $f0)) * (- $f0)) (type: double), $f5 (type: tinyint), (- $f5) (type: tinyint) + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 44 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_13.q.out b/ql/src/test/results/clientpositive/vectorization_13.q.out index 95cb09a..99d5bac 100644 --- a/ql/src/test/results/clientpositive/vectorization_13.q.out +++ b/ql/src/test/results/clientpositive/vectorization_13.q.out @@ -85,11 +85,11 @@ STAGE PLANS: Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: $f0, $f1, $f2, $f3, $f4 Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), sum(_col3), stddev_pop(_col3), stddev_pop(_col1), max(_col3), min(_col1) - keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + aggregations: max($f1), sum($f3), stddev_pop($f3), stddev_pop($f1), max($f3), min($f1) + keys: $f0 (type: boolean), $f1 (type: tinyint), $f2 (type: timestamp), $f3 (type: float), $f4 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE @@ -105,11 +105,11 @@ STAGE PLANS: aggregations: max(VALUE._col0), sum(VALUE._col1), stddev_pop(VALUE._col2), stddev_pop(VALUE._col3), max(VALUE._col4), min(VALUE._col5) keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * UDFToDouble(_col3)) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (UDFToDouble(((- _col1) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col10 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + expressions: $f0 (type: boolean), $f1 (type: tinyint), $f2 (type: timestamp), $f3 (type: float), $f4 (type: string), (- $f1) (type: tinyint), $f5 (type: tinyint), ((- $f1) + $f5) (type: tinyint), $f6 (type: double), ($f6 * UDFToDouble(((- $f1) + $f5))) (type: double), (- $f6) (type: double), (79.553 * UDFToDouble($f3)) (type: double), $f7 (type: double), (- $f6) (type: double), $f8 (type: double), (UDFToDouble(((- $f1) + $f5)) - 10.175) (type: double), (- (- $f6)) (type: double), (-26.28 / (- (- $f6))) (type: double), $f9 (type: float), (($f6 * UDFToDouble(((- $f1) + $f5))) / UDFToDouble($f1)) (type: double), $f10 (type: tinyint) + outputColumnNames: cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -123,13 +123,13 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint) + key expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), c1 (type: tinyint), c2 (type: tinyint), c3 (type: tinyint), c4 (type: double), c5 (type: double), c6 (type: double), c7 (type: double), c8 (type: double), c9 (type: double), c10 (type: double), c11 (type: double), c12 (type: double), c13 (type: double), c14 (type: float), c15 (type: double), c16 (type: tinyint) sort order: +++++++++++++++++++++ Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: double), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: double), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + outputColumnNames: cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 40 @@ -341,11 +341,11 @@ STAGE PLANS: Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: $f0, $f1, $f2, $f3, $f4 Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), sum(_col3), stddev_pop(_col3), stddev_pop(_col1), max(_col3), min(_col1) - keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + aggregations: max($f1), sum($f3), stddev_pop($f3), stddev_pop($f1), max($f3), min($f1) + keys: $f0 (type: boolean), $f1 (type: tinyint), $f2 (type: timestamp), $f3 (type: float), $f4 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE @@ -361,11 +361,11 @@ STAGE PLANS: aggregations: max(VALUE._col0), sum(VALUE._col1), stddev_pop(VALUE._col2), stddev_pop(VALUE._col3), max(VALUE._col4), min(VALUE._col5) keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * UDFToDouble(_col3)) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (UDFToDouble(((- _col1) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col10 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + expressions: $f0 (type: boolean), $f1 (type: tinyint), $f2 (type: timestamp), $f3 (type: float), $f4 (type: string), (- $f1) (type: tinyint), $f5 (type: tinyint), ((- $f1) + $f5) (type: tinyint), $f6 (type: double), ($f6 * UDFToDouble(((- $f1) + $f5))) (type: double), (- $f6) (type: double), (79.553 * UDFToDouble($f3)) (type: double), $f7 (type: double), (- $f6) (type: double), $f8 (type: double), (UDFToDouble(((- $f1) + $f5)) - 10.175) (type: double), (- (- $f6)) (type: double), (-26.28 / (- (- $f6))) (type: double), $f9 (type: float), (($f6 * UDFToDouble(((- $f1) + $f5))) / UDFToDouble($f1)) (type: double), $f10 (type: tinyint) + outputColumnNames: cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -379,13 +379,13 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint) + key expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), c1 (type: tinyint), c2 (type: tinyint), c3 (type: tinyint), c4 (type: double), c5 (type: double), c6 (type: double), c7 (type: double), c8 (type: double), c9 (type: double), c10 (type: double), c11 (type: double), c12 (type: double), c13 (type: double), c14 (type: float), c15 (type: double), c16 (type: tinyint) sort order: +++++++++++++++++++++ Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: double), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: double), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + outputColumnNames: cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 40 diff --git a/ql/src/test/results/clientpositive/vectorization_14.q.out b/ql/src/test/results/clientpositive/vectorization_14.q.out index f5d9b43..b38a92c 100644 --- a/ql/src/test/results/clientpositive/vectorization_14.q.out +++ b/ql/src/test/results/clientpositive/vectorization_14.q.out @@ -85,11 +85,11 @@ STAGE PLANS: Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), (- (-26.28 + cdouble)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5 Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(_col5), max(_col1), stddev_pop(_col1), count(_col1), var_pop(_col1), var_samp(_col1) - keys: _col0 (type: timestamp), _col1 (type: float), _col2 (type: string), _col3 (type: boolean), _col4 (type: double) + aggregations: stddev_samp($f5), max($f1), stddev_pop($f1), count($f1), var_pop($f1), var_samp($f1) + keys: $f0 (type: timestamp), $f1 (type: float), $f2 (type: string), $f3 (type: boolean), $f4 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE @@ -105,11 +105,11 @@ STAGE PLANS: aggregations: stddev_samp(VALUE._col0), max(VALUE._col1), stddev_pop(VALUE._col2), count(VALUE._col3), var_pop(VALUE._col4), var_samp(VALUE._col5) keys: KEY._col0 (type: timestamp), KEY._col1 (type: float), KEY._col2 (type: string), KEY._col3 (type: boolean), KEY._col4 (type: double) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10 Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: timestamp), _col1 (type: float), _col2 (type: string), _col3 (type: boolean), _col4 (type: double), (-26.28 + _col4) (type: double), (- (-26.28 + _col4)) (type: double), _col5 (type: double), (UDFToDouble(_col1) * -26.28) (type: double), _col6 (type: float), (- _col1) (type: float), (- _col6) (type: float), ((- (-26.28 + _col4)) / 10.175) (type: double), _col7 (type: double), _col8 (type: bigint), (- ((- (-26.28 + _col4)) / 10.175)) (type: double), (-1.389 % _col5) (type: double), (UDFToDouble(_col1) - _col4) (type: double), _col9 (type: double), (_col9 % 10.175) (type: double), _col10 (type: double), (- (UDFToDouble(_col1) - _col4)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 + expressions: $f0 (type: timestamp), $f1 (type: float), $f2 (type: string), $f3 (type: boolean), $f4 (type: double), (-26.28 + $f4) (type: double), (- (-26.28 + $f4)) (type: double), $f5 (type: double), (UDFToDouble($f1) * -26.28) (type: double), $f6 (type: float), (- $f1) (type: float), (- $f6) (type: float), ((- (-26.28 + $f4)) / 10.175) (type: double), $f7 (type: double), $f8 (type: bigint), (- ((- (-26.28 + $f4)) / 10.175)) (type: double), (-1.389 % $f5) (type: double), (UDFToDouble($f1) - $f4) (type: double), $f9 (type: double), ($f9 % 10.175) (type: double), $f10 (type: double), (- (UDFToDouble($f1) - $f4)) (type: double) + outputColumnNames: ctimestamp1, cfloat, cstring1, cboolean1, cdouble, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20, _o__c21 Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -123,14 +123,14 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp) + key expressions: cstring1 (type: string), cfloat (type: float), cdouble (type: double), ctimestamp1 (type: timestamp) sort order: ++++ Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: boolean), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: float), _col10 (type: float), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: bigint), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double) + value expressions: cboolean1 (type: boolean), _o__c5 (type: double), _o__c6 (type: double), _o__c7 (type: double), _o__c8 (type: double), _o__c9 (type: float), _o__c10 (type: float), _o__c11 (type: float), _o__c12 (type: double), _o__c13 (type: double), _o__c14 (type: bigint), _o__c15 (type: double), _o__c16 (type: double), _o__c17 (type: double), _o__c18 (type: double), _o__c19 (type: double), _o__c20 (type: double), _o__c21 (type: double) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey3 (type: timestamp), KEY.reducesinkkey1 (type: float), KEY.reducesinkkey0 (type: string), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: float), VALUE._col6 (type: float), VALUE._col7 (type: float), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: bigint), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double), VALUE._col16 (type: double), VALUE._col17 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 + expressions: KEY.reducesinkkey3 (type: timestamp), KEY.reducesinkkey1 (type: float), KEY.reducesinkkey0 (type: string), VALUE.cboolean1 (type: boolean), KEY.reducesinkkey2 (type: double), VALUE._o__c5 (type: double), VALUE._o__c6 (type: double), VALUE._o__c7 (type: double), VALUE._o__c8 (type: double), VALUE._o__c9 (type: float), VALUE._o__c10 (type: float), VALUE._o__c11 (type: float), VALUE._o__c12 (type: double), VALUE._o__c13 (type: double), VALUE._o__c14 (type: bigint), VALUE._o__c15 (type: double), VALUE._o__c16 (type: double), VALUE._o__c17 (type: double), VALUE._o__c18 (type: double), VALUE._o__c19 (type: double), VALUE._o__c20 (type: double), VALUE._o__c21 (type: double) + outputColumnNames: ctimestamp1, cfloat, cstring1, cboolean1, cdouble, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20, _o__c21 Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vectorization_15.q.out b/ql/src/test/results/clientpositive/vectorization_15.q.out index da0e8e0..c9ade99 100644 --- a/ql/src/test/results/clientpositive/vectorization_15.q.out +++ b/ql/src/test/results/clientpositive/vectorization_15.q.out @@ -81,11 +81,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(_col0), min(_col2), stddev_samp(_col4), var_pop(_col4), var_samp(_col5), stddev_pop(_col5) - keys: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) + aggregations: stddev_samp($f0), min($f2), stddev_samp($f4), var_pop($f4), var_samp($f5), stddev_pop($f5) + keys: $f0 (type: float), $f1 (type: boolean), $f2 (type: double), $f3 (type: string), $f4 (type: tinyint), $f5 (type: int), $f6 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -101,11 +101,11 @@ STAGE PLANS: aggregations: stddev_samp(VALUE._col0), min(VALUE._col1), stddev_samp(VALUE._col2), var_pop(VALUE._col3), var_samp(VALUE._col4), stddev_pop(VALUE._col5) keys: KEY._col0 (type: float), KEY._col1 (type: boolean), KEY._col2 (type: double), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int), KEY._col6 (type: timestamp) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), _col7 (type: double), (-26.28 - UDFToDouble(_col5)) (type: double), _col8 (type: double), (_col2 * 79.553) (type: double), (33.0 % _col0) (type: float), _col9 (type: double), _col10 (type: double), (-23.0 % _col2) (type: double), (- _col4) (type: tinyint), _col11 (type: double), (UDFToFloat(_col5) - _col0) (type: float), (-23 % UDFToInteger(_col4)) (type: int), (- (-26.28 - UDFToDouble(_col5))) (type: double), _col12 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + expressions: $f0 (type: float), $f1 (type: boolean), $f2 (type: double), $f3 (type: string), $f4 (type: tinyint), $f5 (type: int), $f6 (type: timestamp), $f7 (type: double), (-26.28 - UDFToDouble($f5)) (type: double), $f8 (type: double), ($f2 * 79.553) (type: double), (33.0 % $f0) (type: float), $f9 (type: double), $f10 (type: double), (-23.0 % $f2) (type: double), (- $f4) (type: tinyint), $f11 (type: double), (UDFToFloat($f5) - $f0) (type: float), (-23 % UDFToInteger($f4)) (type: int), (- (-26.28 - UDFToDouble($f5))) (type: double), $f12 (type: double) + outputColumnNames: cfloat, cboolean1, cdouble, cstring1, ctinyint, cint, ctimestamp1, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -119,14 +119,14 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) + key expressions: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp) sort order: +++++++ Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE - value expressions: _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: tinyint), _col16 (type: double), _col17 (type: float), _col18 (type: int), _col19 (type: double), _col20 (type: double) + value expressions: _o__c7 (type: double), _o__c8 (type: double), _o__c9 (type: double), _o__c10 (type: double), _o__c11 (type: float), _o__c12 (type: double), _o__c13 (type: double), _o__c14 (type: double), _o__c15 (type: tinyint), _o__c16 (type: double), _o__c17 (type: float), _o__c18 (type: int), _o__c19 (type: double), _o__c20 (type: double) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: float), KEY.reducesinkkey1 (type: boolean), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: tinyint), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: timestamp), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: tinyint), VALUE._col9 (type: double), VALUE._col10 (type: float), VALUE._col11 (type: int), VALUE._col12 (type: double), VALUE._col13 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + expressions: KEY.reducesinkkey0 (type: float), KEY.reducesinkkey1 (type: boolean), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: tinyint), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: timestamp), VALUE._o__c7 (type: double), VALUE._o__c8 (type: double), VALUE._o__c9 (type: double), VALUE._o__c10 (type: double), VALUE._o__c11 (type: float), VALUE._o__c12 (type: double), VALUE._o__c13 (type: double), VALUE._o__c14 (type: double), VALUE._o__c15 (type: tinyint), VALUE._o__c16 (type: double), VALUE._o__c17 (type: float), VALUE._o__c18 (type: int), VALUE._o__c19 (type: double), VALUE._o__c20 (type: double) + outputColumnNames: cfloat, cboolean1, cdouble, cstring1, ctinyint, cint, ctimestamp1, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vectorization_16.q.out b/ql/src/test/results/clientpositive/vectorization_16.q.out index 6ae3b4e..55170db 100644 --- a/ql/src/test/results/clientpositive/vectorization_16.q.out +++ b/ql/src/test/results/clientpositive/vectorization_16.q.out @@ -58,11 +58,11 @@ STAGE PLANS: Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), stddev_samp(_col1), min(_col1) - keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + aggregations: count($f1), stddev_samp($f1), min($f1) + keys: $f0 (type: string), $f1 (type: double), $f2 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE @@ -78,11 +78,11 @@ STAGE PLANS: aggregations: count(VALUE._col0), stddev_samp(VALUE._col1), min(VALUE._col2) keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5 Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639) (type: double), (- (_col1 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + expressions: $f0 (type: string), $f1 (type: double), $f2 (type: timestamp), ($f1 - 9763215.5639) (type: double), (- ($f1 - 9763215.5639)) (type: double), $f3 (type: bigint), $f4 (type: double), (- $f4) (type: double), ($f4 * UDFToDouble($f3)) (type: double), $f5 (type: double), (9763215.5639 / $f1) (type: double), (UDFToDouble($f3) / -1.389) (type: double), $f4 (type: double) + outputColumnNames: cstring1, cdouble, ctimestamp1, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12 Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vectorization_17.q.out b/ql/src/test/results/clientpositive/vectorization_17.q.out index 3d58e68..204a02f 100644 --- a/ql/src/test/results/clientpositive/vectorization_17.q.out +++ b/ql/src/test/results/clientpositive/vectorization_17.q.out @@ -66,18 +66,18 @@ STAGE PLANS: Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float), cstring1 (type: string), cint (type: int), ctimestamp1 (type: timestamp), cdouble (type: double), cbigint (type: bigint), (UDFToDouble(cfloat) / UDFToDouble(ctinyint)) (type: double), (UDFToLong(cint) % cbigint) (type: bigint), (- cdouble) (type: double), (cdouble + (UDFToDouble(cfloat) / UDFToDouble(ctinyint))) (type: double), (cdouble / UDFToDouble(cint)) (type: double), (- (- cdouble)) (type: double), (9763215.5639 % UDFToDouble(cbigint)) (type: double), (2563.58 + (- (- cdouble))) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + outputColumnNames: cfloat, cstring1, cint, ctimestamp1, cdouble, cbigint, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13 Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col5 (type: bigint), _col0 (type: float) + key expressions: cbigint (type: bigint), cfloat (type: float) sort order: ++ Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: timestamp), _col4 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double) + value expressions: cstring1 (type: string), cint (type: int), ctimestamp1 (type: timestamp), cdouble (type: double), _o__c6 (type: double), _o__c7 (type: bigint), _o__c8 (type: double), _o__c9 (type: double), _o__c10 (type: double), _o__c11 (type: double), _o__c12 (type: double), _o__c13 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey1 (type: float), VALUE._col0 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: timestamp), VALUE._col3 (type: double), KEY.reducesinkkey0 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: bigint), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + expressions: KEY.reducesinkkey1 (type: float), VALUE.cstring1 (type: string), VALUE.cint (type: int), VALUE.ctimestamp1 (type: timestamp), VALUE.cdouble (type: double), KEY.reducesinkkey0 (type: bigint), VALUE._o__c6 (type: double), VALUE._o__c7 (type: bigint), VALUE._o__c8 (type: double), VALUE._o__c9 (type: double), VALUE._o__c10 (type: double), VALUE._o__c11 (type: double), VALUE._o__c12 (type: double), VALUE._o__c13 (type: double) + outputColumnNames: cfloat, cstring1, cint, ctimestamp1, cdouble, cbigint, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13 Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vectorization_7.q.out b/ql/src/test/results/clientpositive/vectorization_7.q.out index 6e2a0ea..551cf55 100644 --- a/ql/src/test/results/clientpositive/vectorization_7.q.out +++ b/ql/src/test/results/clientpositive/vectorization_7.q.out @@ -72,17 +72,17 @@ STAGE PLANS: Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + outputColumnNames: cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) + key expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), c1 (type: bigint), c2 (type: int), c3 (type: smallint), c4 (type: tinyint), c5 (type: int), c6 (type: bigint), c7 (type: int), c8 (type: tinyint), c9 (type: tinyint) sort order: +++++++++++++++ Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + outputColumnNames: cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 25 @@ -254,17 +254,17 @@ STAGE PLANS: Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + outputColumnNames: cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) + key expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), c1 (type: bigint), c2 (type: int), c3 (type: smallint), c4 (type: tinyint), c5 (type: int), c6 (type: bigint), c7 (type: int), c8 (type: tinyint), c9 (type: tinyint) sort order: +++++++++++++++ Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + outputColumnNames: cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 25 diff --git a/ql/src/test/results/clientpositive/vectorization_8.q.out b/ql/src/test/results/clientpositive/vectorization_8.q.out index c38fad1..40e6f84 100644 --- a/ql/src/test/results/clientpositive/vectorization_8.q.out +++ b/ql/src/test/results/clientpositive/vectorization_8.q.out @@ -68,17 +68,17 @@ STAGE PLANS: Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15 - cdouble) (type: double), (cdouble * -257.0) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - UDFToDouble(cfloat)) (type: double), (- cfloat) (type: float), ((-5638.15 - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + outputColumnNames: ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: timestamp), _col1 (type: double), _col2 (type: boolean), _col3 (type: string), _col4 (type: float), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: float), _col13 (type: double) + key expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), c1 (type: double), c2 (type: double), c3 (type: double), c4 (type: float), c5 (type: double), c6 (type: double), c7 (type: double), c8 (type: float), c9 (type: double) sort order: ++++++++++++++ Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: boolean), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: float), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey7 (type: double), KEY.reducesinkkey8 (type: float), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey11 (type: double), KEY.reducesinkkey12 (type: float), KEY.reducesinkkey13 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + outputColumnNames: ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 @@ -237,17 +237,17 @@ STAGE PLANS: Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15 - cdouble) (type: double), (cdouble * -257.0) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - UDFToDouble(cfloat)) (type: double), (- cfloat) (type: float), ((-5638.15 - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + outputColumnNames: ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: timestamp), _col1 (type: double), _col2 (type: boolean), _col3 (type: string), _col4 (type: float), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: float), _col13 (type: double) + key expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), c1 (type: double), c2 (type: double), c3 (type: double), c4 (type: float), c5 (type: double), c6 (type: double), c7 (type: double), c8 (type: float), c9 (type: double) sort order: ++++++++++++++ Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: boolean), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: float), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey7 (type: double), KEY.reducesinkkey8 (type: float), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey11 (type: double), KEY.reducesinkkey12 (type: float), KEY.reducesinkkey13 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + outputColumnNames: ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 diff --git a/ql/src/test/results/clientpositive/vectorization_9.q.out b/ql/src/test/results/clientpositive/vectorization_9.q.out index 6ae3b4e..55170db 100644 --- a/ql/src/test/results/clientpositive/vectorization_9.q.out +++ b/ql/src/test/results/clientpositive/vectorization_9.q.out @@ -58,11 +58,11 @@ STAGE PLANS: Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), stddev_samp(_col1), min(_col1) - keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + aggregations: count($f1), stddev_samp($f1), min($f1) + keys: $f0 (type: string), $f1 (type: double), $f2 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE @@ -78,11 +78,11 @@ STAGE PLANS: aggregations: count(VALUE._col0), stddev_samp(VALUE._col1), min(VALUE._col2) keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5 Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639) (type: double), (- (_col1 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + expressions: $f0 (type: string), $f1 (type: double), $f2 (type: timestamp), ($f1 - 9763215.5639) (type: double), (- ($f1 - 9763215.5639)) (type: double), $f3 (type: bigint), $f4 (type: double), (- $f4) (type: double), ($f4 * UDFToDouble($f3)) (type: double), $f5 (type: double), (9763215.5639 / $f1) (type: double), (UDFToDouble($f3) / -1.389) (type: double), $f4 (type: double) + outputColumnNames: cstring1, cdouble, ctimestamp1, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12 Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vectorization_decimal_date.q.out b/ql/src/test/results/clientpositive/vectorization_decimal_date.q.out index ebbb24f..1e1683b 100644 --- a/ql/src/test/results/clientpositive/vectorization_decimal_date.q.out +++ b/ql/src/test/results/clientpositive/vectorization_decimal_date.q.out @@ -28,7 +28,7 @@ STAGE PLANS: Statistics: Num rows: 3072 Data size: 412815 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdate (type: date), cdecimal (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: cdate, cdecimal Statistics: Num rows: 3072 Data size: 412815 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 diff --git a/ql/src/test/results/clientpositive/vectorization_div0.q.out b/ql/src/test/results/clientpositive/vectorization_div0.q.out index 9cd35d3..c46315b 100644 --- a/ql/src/test/results/clientpositive/vectorization_div0.q.out +++ b/ql/src/test/results/clientpositive/vectorization_div0.q.out @@ -19,7 +19,7 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cdouble / 0.0) (type: double) - outputColumnNames: _col0 + outputColumnNames: _o__c0 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 @@ -177,18 +177,18 @@ STAGE PLANS: Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cbigint - 988888) (type: bigint), (cdouble / UDFToDouble((cbigint - 988888))) (type: double), (1.2 / UDFToDouble((cbigint - 988888))) (type: double) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: s1, s2, _o__c2 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: bigint), _col1 (type: double) + key expressions: s1 (type: bigint), s2 (type: double) sort order: ++ Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: double) + value expressions: _o__c2 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: double) - outputColumnNames: _col0, _col1, _col2 + expressions: KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey1 (type: double), VALUE._o__c2 (type: double) + outputColumnNames: s1, s2, _o__c2 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 @@ -344,19 +344,19 @@ STAGE PLANS: predicate: ((cdouble >= -500.0) and (cdouble < -199.0)) (type: boolean) Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (cdouble + 200.0) (type: double), (UDFToDouble(cbigint) / (cdouble + 200.0)) (type: double), ((cdouble + 200.0) / (cdouble + 200.0)) (type: double), (3.0 / (cdouble + 200.0)) (type: double), (1.2 / (cdouble + 200.0)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col4, _col5 + expressions: ((cdouble + 200.0) / (cdouble + 200.0)) (type: double), (3.0 / (cdouble + 200.0)) (type: double), (1.2 / (cdouble + 200.0)) (type: double), (cdouble + 200.0) (type: double), (UDFToDouble(cbigint) / (cdouble + 200.0)) (type: double) + outputColumnNames: _o__c2, _o__c4, _o__c5, s1, s2 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: double), _col1 (type: double) + key expressions: s1 (type: double), s2 (type: double) sort order: ++ Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: double), _col4 (type: double), _col5 (type: double) + value expressions: _o__c2 (type: double), _o__c4 (type: double), _o__c5 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: double), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: double), KEY.reducesinkkey1 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + expressions: KEY.reducesinkkey0 (type: double), KEY.reducesinkkey1 (type: double), VALUE._o__c2 (type: double), KEY.reducesinkkey1 (type: double), VALUE._o__c4 (type: double), VALUE._o__c5 (type: double) + outputColumnNames: s1, s2, _o__c2, _o__c3, _o__c4, _o__c5 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 diff --git a/ql/src/test/results/clientpositive/vectorization_limit.q.out b/ql/src/test/results/clientpositive/vectorization_limit.q.out index 7691a4d..1d75c9e 100644 --- a/ql/src/test/results/clientpositive/vectorization_limit.q.out +++ b/ql/src/test/results/clientpositive/vectorization_limit.q.out @@ -19,7 +19,7 @@ STAGE PLANS: Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cdouble (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: cbigint, cdouble Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 7 @@ -81,19 +81,19 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double), csmallint (type: smallint) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: ctinyint, cdouble, csmallint Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: tinyint), _col1 (type: double) + key expressions: ctinyint (type: tinyint), cdouble (type: double) sort order: ++ Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 - value expressions: _col2 (type: smallint) + value expressions: csmallint (type: smallint) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: smallint) - outputColumnNames: _col0, _col1, _col2 + expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), VALUE.csmallint (type: smallint) + outputColumnNames: ctinyint, cdouble, csmallint Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 @@ -161,11 +161,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), (cdouble + 1.0) (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col1) - keys: _col0 (type: tinyint) + aggregations: avg($f1) + keys: $f0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -182,18 +182,22 @@ STAGE PLANS: aggregations: avg(VALUE._col0) keys: KEY._col0 (type: tinyint) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: tinyint), $f1 (type: double) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 20 Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -250,10 +254,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: tinyint) + keys: ctinyint (type: tinyint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -268,18 +272,22 @@ STAGE PLANS: Group By Operator keys: KEY._col0 (type: tinyint) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: ctinyint + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 20 Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -334,11 +342,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: tinyint), _col1 (type: double) + aggregations: count(DISTINCT cdouble) + keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -354,18 +362,22 @@ STAGE PLANS: aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: tinyint) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, $f1 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: ctinyint (type: tinyint), $f1 (type: bigint) + outputColumnNames: ctinyint, $f1 + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 20 Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -452,11 +464,11 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: double) + aggregations: sum($f1) + keys: $f0 (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE @@ -472,28 +484,32 @@ STAGE PLANS: aggregations: sum(VALUE._col0) keys: KEY._col0 (type: double) mode: mergepartial - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: double), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col1 (type: bigint), _col0 (type: double) + key expressions: $f1 (type: bigint), $f0 (type: double) sort order: ++ Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: double), KEY.reducesinkkey0 (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 diff --git a/ql/src/test/results/clientpositive/vectorization_part_project.q.out b/ql/src/test/results/clientpositive/vectorization_part_project.q.out index f98e79c..f596b49 100644 --- a/ql/src/test/results/clientpositive/vectorization_part_project.q.out +++ b/ql/src/test/results/clientpositive/vectorization_part_project.q.out @@ -63,17 +63,17 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 54496 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cdouble + 2.0) (type: double) - outputColumnNames: _col0 + outputColumnNames: c1 Statistics: Num rows: 200 Data size: 54496 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: double) + key expressions: c1 (type: double) sort order: + Statistics: Num rows: 200 Data size: 54496 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: double) - outputColumnNames: _col0 + outputColumnNames: c1 Statistics: Num rows: 200 Data size: 54496 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 diff --git a/ql/src/test/results/clientpositive/vectorization_pushdown.q.out b/ql/src/test/results/clientpositive/vectorization_pushdown.q.out index 7205376..6d9ee1b 100644 --- a/ql/src/test/results/clientpositive/vectorization_pushdown.q.out +++ b/ql/src/test/results/clientpositive/vectorization_pushdown.q.out @@ -20,10 +20,10 @@ STAGE PLANS: Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0) + aggregations: avg($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -36,15 +36,19 @@ STAGE PLANS: Group By Operator aggregations: avg(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: double) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/vectorization_short_regress.q.out index 728f628..2dccc1b 100644 --- a/ql/src/test/results/clientpositive/vectorization_short_regress.q.out +++ b/ql/src/test/results/clientpositive/vectorization_short_regress.q.out @@ -151,10 +151,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdouble (type: double), csmallint (type: smallint), cfloat (type: float), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: $f0, $f1, $f2, $f3, $f4 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), sum(_col1), stddev_pop(_col0), stddev_samp(_col2), var_samp(_col0), avg(_col3), stddev_samp(_col0), min(_col4), count(_col2) + aggregations: avg($f0), sum($f1), stddev_pop($f0), stddev_samp($f2), var_samp($f0), avg($f3), stddev_samp($f0), min($f4), count($f2) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE @@ -167,15 +167,15 @@ STAGE PLANS: Group By Operator aggregations: avg(VALUE._col0), sum(VALUE._col1), stddev_pop(VALUE._col2), stddev_samp(VALUE._col3), var_samp(VALUE._col4), avg(VALUE._col5), stddev_samp(VALUE._col6), min(VALUE._col7), count(VALUE._col8) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 68 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8 + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), (_col0 + -3728.0) (type: double), (- (_col0 + -3728.0)) (type: double), (- (- (_col0 + -3728.0))) (type: double), ((- (- (_col0 + -3728.0))) * (_col0 + -3728.0)) (type: double), _col1 (type: double), (- _col0) (type: double), _col2 (type: double), (((- (- (_col0 + -3728.0))) * (_col0 + -3728.0)) * (- (- (_col0 + -3728.0)))) (type: double), _col3 (type: double), (- _col2) (type: double), (_col2 - (- (- (_col0 + -3728.0)))) (type: double), ((_col2 - (- (- (_col0 + -3728.0)))) * _col2) (type: double), _col4 (type: double), _col5 (type: double), (10.175 - _col4) (type: double), (- (10.175 - _col4)) (type: double), ((- _col2) / -563.0) (type: double), _col6 (type: double), (- ((- _col2) / -563.0)) (type: double), (_col0 / _col1) (type: double), _col7 (type: tinyint), _col8 (type: bigint), (UDFToDouble(_col7) / ((- _col2) / -563.0)) (type: double), (- (_col0 / _col1)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24 - Statistics: Num rows: 1 Data size: 68 Basic stats: COMPLETE Column stats: NONE + expressions: $f0 (type: double), ($f0 + -3728.0) (type: double), (- ($f0 + -3728.0)) (type: double), (- (- ($f0 + -3728.0))) (type: double), ((- (- ($f0 + -3728.0))) * ($f0 + -3728.0)) (type: double), $f1 (type: double), (- $f0) (type: double), $f2 (type: double), (((- (- ($f0 + -3728.0))) * ($f0 + -3728.0)) * (- (- ($f0 + -3728.0)))) (type: double), $f3 (type: double), (- $f2) (type: double), ($f2 - (- (- ($f0 + -3728.0)))) (type: double), (($f2 - (- (- ($f0 + -3728.0)))) * $f2) (type: double), $f4 (type: double), $f5 (type: double), (10.175 - $f4) (type: double), (- (10.175 - $f4)) (type: double), ((- $f2) / -563.0) (type: double), $f6 (type: double), (- ((- $f2) / -563.0)) (type: double), ($f0 / $f1) (type: double), $f7 (type: tinyint), $f8 (type: bigint), (UDFToDouble($f7) / ((- $f2) / -563.0)) (type: double), (- ($f0 / $f1)) (type: double) + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20, _o__c21, _o__c22, _o__c23, _o__c24 + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 68 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -357,10 +357,10 @@ STAGE PLANS: Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cbigint (type: bigint), csmallint (type: smallint), cdouble (type: double), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: $f0, $f1, $f2, $f3, $f4 Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0), var_pop(_col1), stddev_pop(_col2), max(_col3), avg(_col4), min(_col0), min(_col3), stddev_samp(_col2), var_samp(_col0) + aggregations: max($f0), var_pop($f1), stddev_pop($f2), max($f3), avg($f4), min($f0), min($f3), stddev_samp($f2), var_samp($f0) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -373,15 +373,15 @@ STAGE PLANS: Group By Operator aggregations: max(VALUE._col0), var_pop(VALUE._col1), stddev_pop(VALUE._col2), max(VALUE._col3), avg(VALUE._col4), min(VALUE._col5), min(VALUE._col6), stddev_samp(VALUE._col7), var_samp(VALUE._col8) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8 + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), (UDFToDouble(_col0) / -3728.0) (type: double), (_col0 * -3728) (type: int), _col1 (type: double), (- (_col0 * -3728)) (type: int), _col2 (type: double), (-563 % (_col0 * -3728)) (type: int), (_col1 / _col2) (type: double), (- _col2) (type: double), _col3 (type: double), _col4 (type: double), (_col2 - 10.175) (type: double), _col5 (type: int), (UDFToDouble((_col0 * -3728)) % (_col2 - 10.175)) (type: double), (- _col3) (type: double), _col6 (type: double), (_col3 % -26.28) (type: double), _col7 (type: double), (- (UDFToDouble(_col0) / -3728.0)) (type: double), ((- (_col0 * -3728)) % (-563 % (_col0 * -3728))) (type: int), ((UDFToDouble(_col0) / -3728.0) - _col4) (type: double), (- (_col0 * -3728)) (type: int), _col8 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22 - Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + expressions: $f0 (type: int), (UDFToDouble($f0) / -3728.0) (type: double), ($f0 * -3728) (type: int), $f1 (type: double), (- ($f0 * -3728)) (type: int), $f2 (type: double), (-563 % ($f0 * -3728)) (type: int), ($f1 / $f2) (type: double), (- $f2) (type: double), $f3 (type: double), $f4 (type: double), ($f2 - 10.175) (type: double), $f5 (type: int), (UDFToDouble(($f0 * -3728)) % ($f2 - 10.175)) (type: double), (- $f3) (type: double), $f6 (type: double), ($f3 % -26.28) (type: double), $f7 (type: double), (- (UDFToDouble($f0) / -3728.0)) (type: double), ((- ($f0 * -3728)) % (-563 % ($f0 * -3728))) (type: int), ((UDFToDouble($f0) / -3728.0) - $f4) (type: double), (- ($f0 * -3728)) (type: int), $f8 (type: double) + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20, _o__c21, _o__c22 + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -554,10 +554,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cdouble (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: $f0, $f1, $f2, $f3, $f4 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: var_pop(_col0), count(), max(_col1), stddev_pop(_col2), max(_col3), stddev_samp(_col4), count(_col1), avg(_col1) + aggregations: var_pop($f0), count(), max($f1), stddev_pop($f2), max($f3), stddev_samp($f4), count($f1), avg($f1) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -570,15 +570,15 @@ STAGE PLANS: Group By Operator aggregations: var_pop(VALUE._col0), count(VALUE._col1), max(VALUE._col2), stddev_pop(VALUE._col3), max(VALUE._col4), stddev_samp(VALUE._col5), count(VALUE._col6), avg(VALUE._col7) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7 + Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), (- _col0) (type: double), (_col0 - (- _col0)) (type: double), _col1 (type: bigint), (UDFToDouble(_col1) % 79.553) (type: double), _col2 (type: tinyint), (UDFToDouble(_col1) - (- _col0)) (type: double), (- (- _col0)) (type: double), (-1.0 % (- _col0)) (type: double), _col1 (type: bigint), (- _col1) (type: bigint), _col3 (type: double), (- (- (- _col0))) (type: double), (762 * (- _col1)) (type: bigint), _col4 (type: int), (UDFToLong(_col2) + (762 * (- _col1))) (type: bigint), ((- _col0) + UDFToDouble(_col4)) (type: double), _col5 (type: double), ((- _col1) % _col1) (type: bigint), _col6 (type: bigint), _col7 (type: double), (-3728 % (UDFToLong(_col2) + (762 * (- _col1)))) (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE + expressions: $f0 (type: double), (- $f0) (type: double), ($f0 - (- $f0)) (type: double), $f1 (type: bigint), (UDFToDouble($f1) % 79.553) (type: double), $f2 (type: tinyint), (UDFToDouble($f1) - (- $f0)) (type: double), (- (- $f0)) (type: double), (-1.0 % (- $f0)) (type: double), $f1 (type: bigint), (- $f1) (type: bigint), $f3 (type: double), (- (- (- $f0))) (type: double), (762 * (- $f1)) (type: bigint), $f4 (type: int), (UDFToLong($f2) + (762 * (- $f1))) (type: bigint), ((- $f0) + UDFToDouble($f4)) (type: double), $f5 (type: double), ((- $f1) % $f1) (type: bigint), $f6 (type: bigint), $f7 (type: double), (-3728 % (UDFToLong($f2) + (762 * (- $f1)))) (type: bigint) + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20, _o__c21 + Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -730,10 +730,10 @@ STAGE PLANS: Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cbigint (type: bigint), cint (type: int), cfloat (type: float) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: $f0, $f1, $f2, $f3 Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), max(_col1), stddev_samp(_col2), var_pop(_col2), var_pop(_col1), max(_col3) + aggregations: avg($f0), max($f1), stddev_samp($f2), var_pop($f2), var_pop($f1), max($f3) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -746,15 +746,15 @@ STAGE PLANS: Group By Operator aggregations: avg(VALUE._col0), max(VALUE._col1), stddev_samp(VALUE._col2), var_pop(VALUE._col3), var_pop(VALUE._col4), max(VALUE._col5) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 44 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5 + Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), (_col0 + 6981.0) (type: double), ((_col0 + 6981.0) + _col0) (type: double), _col1 (type: bigint), (((_col0 + 6981.0) + _col0) / _col0) (type: double), (- (_col0 + 6981.0)) (type: double), _col2 (type: double), (_col0 % (- (_col0 + 6981.0))) (type: double), _col3 (type: double), _col4 (type: double), (- _col1) (type: bigint), (UDFToDouble((- _col1)) / _col2) (type: double), _col5 (type: float), (_col4 * -26.28) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 1 Data size: 44 Basic stats: COMPLETE Column stats: NONE + expressions: $f0 (type: double), ($f0 + 6981.0) (type: double), (($f0 + 6981.0) + $f0) (type: double), $f1 (type: bigint), ((($f0 + 6981.0) + $f0) / $f0) (type: double), (- ($f0 + 6981.0)) (type: double), $f2 (type: double), ($f0 % (- ($f0 + 6981.0))) (type: double), $f3 (type: double), $f4 (type: double), (- $f1) (type: bigint), (UDFToDouble((- $f1)) / $f2) (type: double), $f5 (type: float), ($f4 * -26.28) (type: double) + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13 + Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 44 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -914,17 +914,17 @@ STAGE PLANS: Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdouble (type: double), ctimestamp2 (type: timestamp), cstring1 (type: string), cboolean2 (type: boolean), ctinyint (type: tinyint), cfloat (type: float), ctimestamp1 (type: timestamp), csmallint (type: smallint), cbigint (type: bigint), (-3728 * cbigint) (type: bigint), (- cint) (type: int), (-863.257 - UDFToDouble(cint)) (type: double), (- csmallint) (type: smallint), (csmallint - (- csmallint)) (type: smallint), ((csmallint - (- csmallint)) + (- csmallint)) (type: smallint), (UDFToDouble(cint) / UDFToDouble(cint)) (type: double), ((-863.257 - UDFToDouble(cint)) - -26.28) (type: double), (- cfloat) (type: float), (cdouble * -89010.0) (type: double), (UDFToDouble(ctinyint) / 988888.0) (type: double), (- ctinyint) (type: tinyint), (79.553 / UDFToDouble(ctinyint)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22 + outputColumnNames: cint, cdouble, ctimestamp2, cstring1, cboolean2, ctinyint, cfloat, ctimestamp1, csmallint, cbigint, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13 Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: timestamp), _col3 (type: string), _col4 (type: boolean), _col5 (type: tinyint), _col6 (type: float), _col7 (type: timestamp), _col8 (type: smallint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: int), _col12 (type: double), _col13 (type: smallint), _col14 (type: smallint), _col15 (type: smallint), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: double), _col21 (type: tinyint), _col22 (type: double) + key expressions: cint (type: int), cdouble (type: double), ctimestamp2 (type: timestamp), cstring1 (type: string), cboolean2 (type: boolean), ctinyint (type: tinyint), cfloat (type: float), ctimestamp1 (type: timestamp), csmallint (type: smallint), cbigint (type: bigint), c1 (type: bigint), c2 (type: int), c3 (type: double), c4 (type: smallint), c5 (type: smallint), c6 (type: smallint), c7 (type: double), c8 (type: double), c9 (type: float), c10 (type: double), c11 (type: double), c12 (type: tinyint), c13 (type: double) sort order: +++++++++++++++++++++++ Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: boolean), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: float), KEY.reducesinkkey7 (type: timestamp), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: bigint), KEY.reducesinkkey10 (type: bigint), KEY.reducesinkkey11 (type: int), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey13 (type: smallint), KEY.reducesinkkey14 (type: smallint), KEY.reducesinkkey15 (type: smallint), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: double), KEY.reducesinkkey21 (type: tinyint), KEY.reducesinkkey22 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22 + outputColumnNames: cint, cdouble, ctimestamp2, cstring1, cboolean2, ctinyint, cfloat, ctimestamp1, csmallint, cbigint, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13 Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 50 @@ -1165,17 +1165,17 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cbigint (type: bigint), cstring1 (type: string), cboolean1 (type: boolean), cfloat (type: float), cdouble (type: double), ctimestamp2 (type: timestamp), csmallint (type: smallint), cstring2 (type: string), cboolean2 (type: boolean), (UDFToDouble(cint) / UDFToDouble(cbigint)) (type: double), (UDFToDouble(cbigint) % 79.553) (type: double), (- (UDFToDouble(cint) / UDFToDouble(cbigint))) (type: double), (10.175 % UDFToDouble(cfloat)) (type: double), (- cfloat) (type: float), (cfloat - (- cfloat)) (type: float), ((cfloat - (- cfloat)) % -6432.0) (type: float), (cdouble * UDFToDouble(csmallint)) (type: double), (- cdouble) (type: double), (- cbigint) (type: bigint), (UDFToDouble(cfloat) - (UDFToDouble(cint) / UDFToDouble(cbigint))) (type: double), (- csmallint) (type: smallint), (3569 % cbigint) (type: bigint), (359.0 - cdouble) (type: double), (- csmallint) (type: smallint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24 + outputColumnNames: cint, cbigint, cstring1, cboolean1, cfloat, cdouble, ctimestamp2, csmallint, cstring2, cboolean2, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: string), _col3 (type: boolean), _col4 (type: float), _col5 (type: double), _col6 (type: timestamp), _col7 (type: smallint), _col8 (type: string), _col9 (type: boolean), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: float), _col15 (type: float), _col16 (type: float), _col17 (type: double), _col18 (type: double), _col19 (type: bigint), _col20 (type: double), _col21 (type: smallint), _col22 (type: bigint), _col23 (type: double), _col24 (type: smallint) + key expressions: cint (type: int), cbigint (type: bigint), cstring1 (type: string), cboolean1 (type: boolean), cfloat (type: float), cdouble (type: double), ctimestamp2 (type: timestamp), csmallint (type: smallint), cstring2 (type: string), cboolean2 (type: boolean), c1 (type: double), c2 (type: double), c3 (type: double), c4 (type: double), c5 (type: float), c6 (type: float), c7 (type: float), c8 (type: double), c9 (type: double), c10 (type: bigint), c11 (type: double), c12 (type: smallint), c13 (type: bigint), c14 (type: double), c15 (type: smallint) sort order: +++++++++++++++++++++++++ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: boolean), KEY.reducesinkkey4 (type: float), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: timestamp), KEY.reducesinkkey7 (type: smallint), KEY.reducesinkkey8 (type: string), KEY.reducesinkkey9 (type: boolean), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: double), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey13 (type: double), KEY.reducesinkkey14 (type: float), KEY.reducesinkkey15 (type: float), KEY.reducesinkkey16 (type: float), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: double), KEY.reducesinkkey19 (type: bigint), KEY.reducesinkkey20 (type: double), KEY.reducesinkkey21 (type: smallint), KEY.reducesinkkey22 (type: bigint), KEY.reducesinkkey23 (type: double), KEY.reducesinkkey21 (type: smallint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24 + outputColumnNames: cint, cbigint, cstring1, cboolean1, cfloat, cdouble, ctimestamp2, csmallint, cstring2, cboolean2, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 25 @@ -1365,18 +1365,18 @@ STAGE PLANS: Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cstring1 (type: string), cboolean2 (type: boolean), ctimestamp2 (type: timestamp), cdouble (type: double), cfloat (type: float), cbigint (type: bigint), csmallint (type: smallint), cboolean1 (type: boolean), (cint + UDFToInteger(csmallint)) (type: int), (cbigint - UDFToLong(ctinyint)) (type: bigint), (- cbigint) (type: bigint), (- cfloat) (type: float), ((cbigint - UDFToLong(ctinyint)) + cbigint) (type: bigint), (cdouble / cdouble) (type: double), (- cdouble) (type: double), (UDFToLong((cint + UDFToInteger(csmallint))) * (- cbigint)) (type: bigint), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (-1.389 / UDFToDouble(ctinyint)) (type: double), (UDFToDouble(cbigint) % cdouble) (type: double), (- csmallint) (type: smallint), (UDFToInteger(csmallint) + (cint + UDFToInteger(csmallint))) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 + outputColumnNames: cint, cstring1, cboolean2, ctimestamp2, cdouble, cfloat, cbigint, csmallint, cboolean1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13 Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col8 (type: boolean), _col1 (type: string), _col3 (type: timestamp), _col5 (type: float), _col6 (type: bigint), _col1 (type: string), _col4 (type: double), _col0 (type: int), _col7 (type: smallint), _col4 (type: double), _col9 (type: int), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: float), _col13 (type: bigint), _col14 (type: double), _col15 (type: double), _col16 (type: bigint), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: smallint), _col21 (type: int) + key expressions: cboolean1 (type: boolean), cstring1 (type: string), ctimestamp2 (type: timestamp), cfloat (type: float), cbigint (type: bigint), cstring1 (type: string), cdouble (type: double), cint (type: int), csmallint (type: smallint), cdouble (type: double), c1 (type: int), c2 (type: bigint), c3 (type: bigint), c4 (type: float), c5 (type: bigint), c6 (type: double), c7 (type: double), c8 (type: bigint), c9 (type: double), c10 (type: double), c11 (type: double), c12 (type: smallint), c13 (type: int) sort order: +++++++++++++++++++++++ Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: boolean) + value expressions: cboolean2 (type: boolean) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey7 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: bigint), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: bigint), KEY.reducesinkkey13 (type: float), KEY.reducesinkkey14 (type: bigint), KEY.reducesinkkey15 (type: double), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: bigint), KEY.reducesinkkey18 (type: double), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: double), KEY.reducesinkkey21 (type: smallint), KEY.reducesinkkey22 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 + expressions: KEY.reducesinkkey7 (type: int), KEY.reducesinkkey1 (type: string), VALUE.cboolean2 (type: boolean), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: bigint), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: bigint), KEY.reducesinkkey13 (type: float), KEY.reducesinkkey14 (type: bigint), KEY.reducesinkkey15 (type: double), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: bigint), KEY.reducesinkkey18 (type: double), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: double), KEY.reducesinkkey21 (type: smallint), KEY.reducesinkkey22 (type: int) + outputColumnNames: cint, cstring1, cboolean2, ctimestamp2, cdouble, cfloat, cbigint, csmallint, cboolean1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13 Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 75 @@ -1624,18 +1624,18 @@ STAGE PLANS: Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cstring2 (type: string), cdouble (type: double), cfloat (type: float), cbigint (type: bigint), csmallint (type: smallint), (UDFToDouble(cbigint) / 3569.0) (type: double), (-257 - UDFToInteger(csmallint)) (type: int), (-6432.0 * cfloat) (type: float), (- cdouble) (type: double), (cdouble * 10.175) (type: double), (UDFToDouble((-6432.0 * cfloat)) / UDFToDouble(cfloat)) (type: double), (- cfloat) (type: float), (cint % UDFToInteger(csmallint)) (type: int), (- cdouble) (type: double), (cdouble * (- cdouble)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 + outputColumnNames: ctimestamp1, cstring2, cdouble, cfloat, cbigint, csmallint, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10 Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col5 (type: smallint), _col1 (type: string), _col2 (type: double), _col3 (type: float), _col4 (type: bigint), _col6 (type: double), _col7 (type: int), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: float), _col13 (type: int), _col14 (type: double), _col15 (type: double) + key expressions: csmallint (type: smallint), cstring2 (type: string), cdouble (type: double), cfloat (type: float), cbigint (type: bigint), c1 (type: double), c2 (type: int), c3 (type: float), c4 (type: double), c5 (type: double), c6 (type: double), c7 (type: float), c8 (type: int), c9 (type: double), c10 (type: double) sort order: +++++++++++++++ Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: timestamp) + value expressions: ctimestamp1 (type: timestamp) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: timestamp), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: bigint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: int), KEY.reducesinkkey7 (type: float), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey14 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 + expressions: VALUE.ctimestamp1 (type: timestamp), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: bigint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: int), KEY.reducesinkkey7 (type: float), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey14 (type: double) + outputColumnNames: ctimestamp1, cstring2, cdouble, cfloat, cbigint, csmallint, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10 Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 45 @@ -1825,11 +1825,11 @@ STAGE PLANS: Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), cbigint (type: bigint), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(_col0), sum(_col1), var_pop(_col2), count() - keys: _col0 (type: smallint) + aggregations: stddev_samp($f0), sum($f1), var_pop($f2), count() + keys: $f0 (type: smallint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE @@ -1845,11 +1845,11 @@ STAGE PLANS: aggregations: stddev_samp(VALUE._col0), sum(VALUE._col1), var_pop(VALUE._col2), count(VALUE._col3) keys: KEY._col0 (type: smallint) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: $f0, $f1, $f2, $f3, $f4 Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: smallint), (UDFToInteger(_col0) % -75) (type: int), _col1 (type: double), (-1.389 / UDFToDouble(_col0)) (type: double), _col2 (type: bigint), (UDFToDouble((UDFToInteger(_col0) % -75)) / UDFToDouble(_col2)) (type: double), (- (UDFToInteger(_col0) % -75)) (type: int), _col3 (type: double), (- (- (UDFToInteger(_col0) % -75))) (type: int), _col4 (type: bigint), (_col4 - -89010) (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + expressions: $f0 (type: smallint), (UDFToInteger($f0) % -75) (type: int), $f1 (type: double), (-1.389 / UDFToDouble($f0)) (type: double), $f2 (type: bigint), (UDFToDouble((UDFToInteger($f0) % -75)) / UDFToDouble($f2)) (type: double), (- (UDFToInteger($f0) % -75)) (type: int), $f3 (type: double), (- (- (UDFToInteger($f0) % -75))) (type: int), $f4 (type: bigint), ($f4 - -89010) (type: bigint) + outputColumnNames: csmallint, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10 Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1863,13 +1863,13 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: int), _col7 (type: double), _col8 (type: int), _col9 (type: bigint), _col10 (type: bigint) + key expressions: csmallint (type: smallint), c1 (type: int), c2 (type: double), c3 (type: double), c4 (type: bigint), c5 (type: double), c6 (type: int), c7 (type: double), c8 (type: int), c9 (type: bigint), c10 (type: bigint) sort order: +++++++++++ Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey1 (type: int), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: double), KEY.reducesinkkey4 (type: bigint), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: int), KEY.reducesinkkey7 (type: double), KEY.reducesinkkey8 (type: int), KEY.reducesinkkey9 (type: bigint), KEY.reducesinkkey10 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: csmallint, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10 Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 @@ -2035,11 +2035,11 @@ STAGE PLANS: Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cfloat (type: float) - outputColumnNames: _col0, _col1 + outputColumnNames: $f0, $f1 Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: var_samp(_col0), count(_col1), sum(_col1), var_pop(_col0), stddev_pop(_col0), sum(_col0) - keys: _col0 (type: double) + aggregations: var_samp($f0), count($f1), sum($f1), var_pop($f0), stddev_pop($f0), sum($f0) + keys: $f0 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE @@ -2055,11 +2055,11 @@ STAGE PLANS: aggregations: var_samp(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), var_pop(VALUE._col3), stddev_pop(VALUE._col4), sum(VALUE._col5) keys: KEY._col0 (type: double) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6 Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: double), _col1 (type: double), _col5 (type: double), (_col0 + _col1) (type: double), (_col0 * 762.0) (type: double), _col6 (type: double), (-863.257 % (_col0 * 762.0)) (type: double), (2563.58 * _col1) (type: double), (- _col1) (type: double), _col2 (type: bigint), ((2563.58 * _col1) + -5638.15) (type: double), ((- _col1) * ((2563.58 * _col1) + -5638.15)) (type: double), _col3 (type: double), _col4 (type: double), (_col0 - (- _col1)) (type: double) - outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + expressions: $f1 (type: double), $f5 (type: double), ($f0 + $f1) (type: double), ($f0 * 762.0) (type: double), $f6 (type: double), (-863.257 % ($f0 * 762.0)) (type: double), (2563.58 * $f1) (type: double), (- $f1) (type: double), $f2 (type: bigint), ((2563.58 * $f1) + -5638.15) (type: double), ((- $f1) * ((2563.58 * $f1) + -5638.15)) (type: double), $f3 (type: double), $f4 (type: double), ($f0 - (- $f1)) (type: double), $f0 (type: double) + outputColumnNames: _o__c1, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, cdouble Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2073,14 +2073,14 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: double) + key expressions: cdouble (type: double) sort order: + Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: double) + value expressions: _o__c1 (type: double), _o__c2 (type: double), _o__c3 (type: double), _o__c4 (type: bigint), _o__c5 (type: double), _o__c6 (type: double), _o__c7 (type: double), _o__c8 (type: double), _o__c9 (type: double), _o__c10 (type: double), _o__c11 (type: double), _o__c12 (type: double), _o__c13 (type: double), _o__c14 (type: double) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col12 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 + expressions: KEY.reducesinkkey0 (type: double), VALUE._o__c1 (type: double), VALUE._o__c2 (type: double), VALUE._o__c3 (type: double), VALUE._o__c4 (type: bigint), VALUE._o__c5 (type: double), VALUE._o__c6 (type: double), VALUE._o__c7 (type: double), VALUE._o__c8 (type: double), VALUE._o__c9 (type: double), VALUE._o__c10 (type: double), VALUE._o__c11 (type: double), VALUE._o__c12 (type: double), VALUE._o__c13 (type: double), VALUE._o__c14 (type: double), VALUE._o__c13 (type: double) + outputColumnNames: cdouble, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15 Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2293,11 +2293,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cstring1 (type: string), cint (type: int), csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cdouble (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_pop(_col2), avg(_col3), count(), min(_col4), var_samp(_col3), var_pop(_col5), avg(_col2), var_samp(_col5), avg(_col5), min(_col6), var_pop(_col3), stddev_pop(_col4), sum(_col2) - keys: _col0 (type: timestamp), _col1 (type: string) + aggregations: stddev_pop($f2), avg($f3), count(), min($f4), var_samp($f3), var_pop($f5), avg($f2), var_samp($f5), avg($f5), min($f6), var_pop($f3), stddev_pop($f4), sum($f2) + keys: $f0 (type: timestamp), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -2313,11 +2313,11 @@ STAGE PLANS: aggregations: stddev_pop(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), min(VALUE._col3), var_samp(VALUE._col4), var_pop(VALUE._col5), avg(VALUE._col6), var_samp(VALUE._col7), avg(VALUE._col8), min(VALUE._col9), var_pop(VALUE._col10), stddev_pop(VALUE._col11), sum(VALUE._col12) keys: KEY._col0 (type: timestamp), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: timestamp), _col1 (type: string), _col2 (type: double), (_col2 * 10.175) (type: double), (- _col2) (type: double), _col3 (type: double), (- _col2) (type: double), (-26.28 - _col2) (type: double), _col4 (type: bigint), (- _col4) (type: bigint), ((-26.28 - _col2) * (- _col2)) (type: double), _col5 (type: tinyint), (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4))) (type: double), (- (_col2 * 10.175)) (type: double), _col6 (type: double), (_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- _col2)) (type: double), (UDFToDouble((- _col4)) / _col2) (type: double), _col7 (type: double), (10.175 / _col3) (type: double), _col8 (type: double), _col9 (type: double), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- (_col2 * 10.175))) (type: double), _col10 (type: double), (((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) * 10.175) (type: double), (10.175 % (10.175 / _col3)) (type: double), (- _col5) (type: tinyint), _col11 (type: double), _col12 (type: double), (- ((-26.28 - _col2) * (- _col2))) (type: double), ((- _col2) % _col10) (type: double), (-26.28 / UDFToDouble((- _col5))) (type: double), _col13 (type: double), _col14 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) / _col7) (type: double), (- (- _col4)) (type: bigint), _col4 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) % -26.28) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38 + expressions: $f0 (type: timestamp), $f1 (type: string), $f2 (type: double), ($f2 * 10.175) (type: double), (- $f2) (type: double), $f3 (type: double), (- $f2) (type: double), (-26.28 - $f2) (type: double), $f4 (type: bigint), (- $f4) (type: bigint), ((-26.28 - $f2) * (- $f2)) (type: double), $f5 (type: tinyint), (((-26.28 - $f2) * (- $f2)) * UDFToDouble((- $f4))) (type: double), (- ($f2 * 10.175)) (type: double), $f6 (type: double), ($f6 + (((-26.28 - $f2) * (- $f2)) * UDFToDouble((- $f4)))) (type: double), (- (- $f2)) (type: double), (UDFToDouble((- $f4)) / $f2) (type: double), $f7 (type: double), (10.175 / $f3) (type: double), $f8 (type: double), $f9 (type: double), (($f6 + (((-26.28 - $f2) * (- $f2)) * UDFToDouble((- $f4)))) - (((-26.28 - $f2) * (- $f2)) * UDFToDouble((- $f4)))) (type: double), (- (- ($f2 * 10.175))) (type: double), $f10 (type: double), ((($f6 + (((-26.28 - $f2) * (- $f2)) * UDFToDouble((- $f4)))) - (((-26.28 - $f2) * (- $f2)) * UDFToDouble((- $f4)))) * 10.175) (type: double), (10.175 % (10.175 / $f3)) (type: double), (- $f5) (type: tinyint), $f11 (type: double), $f12 (type: double), (- ((-26.28 - $f2) * (- $f2))) (type: double), ((- $f2) % $f10) (type: double), (-26.28 / UDFToDouble((- $f5))) (type: double), $f13 (type: double), $f14 (type: bigint), (($f6 + (((-26.28 - $f2) * (- $f2)) * UDFToDouble((- $f4)))) / $f7) (type: double), (- (- $f4)) (type: bigint), $f4 (type: bigint), (($f6 + (((-26.28 - $f2) * (- $f2)) * UDFToDouble((- $f4)))) % -26.28) (type: double) + outputColumnNames: ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16, c17, c18, c19, c20, c21, c22, c23, c24, c25, c26, c27, c28, c29, c30, c31, c32, c33, c34, c35, c36, c37 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2331,13 +2331,13 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: timestamp), _col1 (type: string), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: double), _col11 (type: tinyint), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double), _col22 (type: double), _col23 (type: double), _col24 (type: double), _col25 (type: double), _col26 (type: double), _col27 (type: tinyint), _col28 (type: double), _col29 (type: double), _col30 (type: double), _col31 (type: double), _col32 (type: double), _col33 (type: double), _col34 (type: bigint), _col35 (type: double), _col36 (type: bigint), _col37 (type: bigint), _col38 (type: double) + key expressions: ctimestamp1 (type: timestamp), cstring1 (type: string), c1 (type: double), c2 (type: double), c3 (type: double), c4 (type: double), c5 (type: double), c6 (type: double), c7 (type: bigint), c8 (type: bigint), c9 (type: double), c10 (type: tinyint), c11 (type: double), c12 (type: double), c13 (type: double), c14 (type: double), c15 (type: double), c16 (type: double), c17 (type: double), c18 (type: double), c19 (type: double), c20 (type: double), c21 (type: double), c22 (type: double), c23 (type: double), c24 (type: double), c25 (type: double), c26 (type: tinyint), c27 (type: double), c28 (type: double), c29 (type: double), c30 (type: double), c31 (type: double), c32 (type: double), c33 (type: bigint), c34 (type: double), c35 (type: bigint), c36 (type: bigint), c37 (type: double) sort order: +++++++++++++++++++++++++++++++++++++++ Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: double), KEY.reducesinkkey4 (type: double), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey4 (type: double), KEY.reducesinkkey7 (type: double), KEY.reducesinkkey8 (type: bigint), KEY.reducesinkkey9 (type: bigint), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: tinyint), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey13 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: double), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: double), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: double), KEY.reducesinkkey21 (type: double), KEY.reducesinkkey22 (type: double), KEY.reducesinkkey23 (type: double), KEY.reducesinkkey24 (type: double), KEY.reducesinkkey25 (type: double), KEY.reducesinkkey26 (type: double), KEY.reducesinkkey27 (type: tinyint), KEY.reducesinkkey28 (type: double), KEY.reducesinkkey29 (type: double), KEY.reducesinkkey30 (type: double), KEY.reducesinkkey31 (type: double), KEY.reducesinkkey32 (type: double), KEY.reducesinkkey33 (type: double), KEY.reducesinkkey34 (type: bigint), KEY.reducesinkkey35 (type: double), KEY.reducesinkkey36 (type: bigint), KEY.reducesinkkey8 (type: bigint), KEY.reducesinkkey38 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38 + outputColumnNames: ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16, c17, c18, c19, c20, c21, c22, c23, c24, c25, c26, c27, c28, c29, c30, c31, c32, c33, c34, c35, c36, c37 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 50 @@ -2628,11 +2628,11 @@ STAGE PLANS: Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cfloat (type: float), cbigint (type: bigint), cint (type: int), cdouble (type: double), ctinyint (type: tinyint), csmallint (type: smallint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6 Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), sum(_col2), var_samp(_col3), avg(_col4), min(_col2), var_pop(_col2), sum(_col3), stddev_samp(_col5), stddev_pop(_col6), avg(_col3) - keys: _col0 (type: boolean) + aggregations: max($f1), sum($f2), var_samp($f3), avg($f4), min($f2), var_pop($f2), sum($f3), stddev_samp($f5), stddev_pop($f6), avg($f3) + keys: $f0 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE @@ -2648,11 +2648,11 @@ STAGE PLANS: aggregations: max(VALUE._col0), sum(VALUE._col1), var_samp(VALUE._col2), avg(VALUE._col3), min(VALUE._col4), var_pop(VALUE._col5), sum(VALUE._col6), stddev_samp(VALUE._col7), stddev_pop(VALUE._col8), avg(VALUE._col9) keys: KEY._col0 (type: boolean) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10 Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: boolean), _col1 (type: float), ((UDFToDouble(_col2) - 10.175) + _col3) (type: double), _col5 (type: bigint), _col6 (type: double), (- (10.175 + UDFToDouble((- _col1)))) (type: double), (79.553 / _col6) (type: double), (_col3 % (79.553 / _col6)) (type: double), _col7 (type: bigint), _col8 (type: double), (-1.389 * UDFToDouble(_col5)) (type: double), (- _col1) (type: float), (UDFToDouble(_col7) - (-1.389 * UDFToDouble(_col5))) (type: double), _col9 (type: double), (- (UDFToDouble(_col7) - (-1.389 * UDFToDouble(_col5)))) (type: double), _col10 (type: double), (- _col10) (type: double), (_col10 * UDFToDouble(_col7)) (type: double), (-26.28 / UDFToDouble(_col1)) (type: double), _col2 (type: bigint), (UDFToDouble(_col2) - 10.175) (type: double), _col3 (type: double), (_col3 % UDFToDouble(_col1)) (type: double), (10.175 + UDFToDouble((- _col1))) (type: double), _col4 (type: double) - outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19, _col2, _col20, _col21, _col22, _col23, _col24, _col25, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + expressions: $f1 (type: float), ((UDFToDouble($f2) - 10.175) + $f3) (type: double), $f5 (type: bigint), $f6 (type: double), (- (10.175 + UDFToDouble((- $f1)))) (type: double), (79.553 / $f6) (type: double), ($f3 % (79.553 / $f6)) (type: double), $f7 (type: bigint), $f8 (type: double), (-1.389 * UDFToDouble($f5)) (type: double), (- $f1) (type: float), (UDFToDouble($f7) - (-1.389 * UDFToDouble($f5))) (type: double), $f9 (type: double), (- (UDFToDouble($f7) - (-1.389 * UDFToDouble($f5)))) (type: double), $f10 (type: double), (- $f10) (type: double), ($f10 * UDFToDouble($f7)) (type: double), (-26.28 / UDFToDouble($f1)) (type: double), $f2 (type: bigint), (UDFToDouble($f2) - 10.175) (type: double), $f3 (type: double), ($f3 % UDFToDouble($f1)) (type: double), (10.175 + UDFToDouble((- $f1))) (type: double), $f4 (type: double), $f0 (type: boolean) + outputColumnNames: _o__c1, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c17, _o__c18, _o__c19, _o__c2, _o__c20, _o__c21, _o__c22, _o__c23, _o__c24, _o__c25, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, cboolean1 Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2666,14 +2666,14 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: boolean) + key expressions: cboolean1 (type: boolean) sort order: + Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: float), _col2 (type: float), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: bigint), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: double), _col17 (type: bigint), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double), _col22 (type: double), _col23 (type: double), _col24 (type: double), _col25 (type: double) + value expressions: _o__c1 (type: float), _o__c2 (type: float), _o__c3 (type: double), _o__c4 (type: bigint), _o__c5 (type: double), _o__c6 (type: double), _o__c7 (type: double), _o__c8 (type: double), _o__c9 (type: double), _o__c10 (type: double), _o__c11 (type: bigint), _o__c12 (type: double), _o__c13 (type: double), _o__c14 (type: double), _o__c15 (type: double), _o__c17 (type: bigint), _o__c18 (type: double), _o__c19 (type: double), _o__c20 (type: double), _o__c21 (type: double), _o__c22 (type: double), _o__c23 (type: double), _o__c24 (type: double), _o__c25 (type: double) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: boolean), VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: bigint), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col12 (type: double), VALUE._col15 (type: bigint), VALUE._col16 (type: double), VALUE._col17 (type: double), VALUE._col18 (type: double), VALUE._col19 (type: double), VALUE._col20 (type: double), VALUE._col21 (type: double), VALUE._col22 (type: double), VALUE._col23 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25 + expressions: KEY.reducesinkkey0 (type: boolean), VALUE._o__c1 (type: float), VALUE._o__c2 (type: float), VALUE._o__c3 (type: double), VALUE._o__c4 (type: bigint), VALUE._o__c5 (type: double), VALUE._o__c6 (type: double), VALUE._o__c7 (type: double), VALUE._o__c8 (type: double), VALUE._o__c9 (type: double), VALUE._o__c10 (type: double), VALUE._o__c11 (type: bigint), VALUE._o__c12 (type: double), VALUE._o__c13 (type: double), VALUE._o__c14 (type: double), VALUE._o__c15 (type: double), VALUE._o__c13 (type: double), VALUE._o__c17 (type: bigint), VALUE._o__c18 (type: double), VALUE._o__c19 (type: double), VALUE._o__c20 (type: double), VALUE._o__c21 (type: double), VALUE._o__c22 (type: double), VALUE._o__c23 (type: double), VALUE._o__c24 (type: double), VALUE._o__c25 (type: double) + outputColumnNames: cboolean1, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20, _o__c21, _o__c22, _o__c23, _o__c24, _o__c25 Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2819,15 +2819,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2863,10 +2867,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: i (type: int) - outputColumnNames: _col0 + outputColumnNames: i Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(i) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -2879,15 +2883,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -2968,7 +2976,7 @@ STAGE PLANS: alias: alltypesnullorc Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12288 Data size: 49152 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -2983,15 +2991,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -3027,10 +3039,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(ctinyint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3043,15 +3055,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -3087,10 +3103,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3103,15 +3119,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -3147,10 +3167,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) - outputColumnNames: _col0 + outputColumnNames: cfloat Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cfloat) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3163,15 +3183,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -3207,10 +3231,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string) - outputColumnNames: _col0 + outputColumnNames: cstring1 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cstring1) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3223,15 +3247,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -3267,10 +3295,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean) - outputColumnNames: _col0 + outputColumnNames: cboolean1 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cboolean1) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3283,15 +3311,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vectorized_case.q.out b/ql/src/test/results/clientpositive/vectorized_case.q.out index 73bf12d..bcb683f 100644 --- a/ql/src/test/results/clientpositive/vectorized_case.q.out +++ b/ql/src/test/results/clientpositive/vectorized_case.q.out @@ -50,7 +50,7 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE ('c') END (type: string), CASE (csmallint) WHEN (418) THEN ('a') WHEN (12205) THEN ('b') ELSE ('c') END (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: csmallint, _o__c1, _o__c2 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vectorized_casts.q.out b/ql/src/test/results/clientpositive/vectorized_casts.q.out index 3c28064..2dccb9e 100644 --- a/ql/src/test/results/clientpositive/vectorized_casts.q.out +++ b/ql/src/test/results/clientpositive/vectorized_casts.q.out @@ -172,7 +172,7 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToBoolean(ctinyint) (type: boolean), UDFToBoolean(csmallint) (type: boolean), UDFToBoolean(cint) (type: boolean), UDFToBoolean(cbigint) (type: boolean), UDFToBoolean(cfloat) (type: boolean), UDFToBoolean(cdouble) (type: boolean), cboolean1 (type: boolean), UDFToBoolean((cbigint * 0)) (type: boolean), UDFToBoolean(ctimestamp1) (type: boolean), UDFToBoolean(cstring1) (type: boolean), UDFToInteger(ctinyint) (type: int), UDFToInteger(csmallint) (type: int), cint (type: int), UDFToInteger(cbigint) (type: int), UDFToInteger(cfloat) (type: int), UDFToInteger(cdouble) (type: int), UDFToInteger(cboolean1) (type: int), UDFToInteger(ctimestamp1) (type: int), UDFToInteger(cstring1) (type: int), UDFToInteger(substr(cstring1, 1, 1)) (type: int), UDFToByte(cfloat) (type: tinyint), UDFToShort(cfloat) (type: smallint), UDFToLong(cfloat) (type: bigint), UDFToDouble(ctinyint) (type: double), UDFToDouble(csmallint) (type: double), UDFToDouble(cint) (type: double), UDFToDouble(cbigint) (type: double), UDFToDouble(cfloat) (type: double), cdouble (type: double), UDFToDouble(cboolean1) (type: double), UDFToDouble(ctimestamp1) (type: double), UDFToDouble(cstring1) (type: double), UDFToDouble(substr(cstring1, 1, 1)) (type: double), UDFToFloat(cint) (type: float), UDFToFloat(cdouble) (type: float), CAST( ctinyint AS TIMESTAMP) (type: timestamp), CAST( csmallint AS TIMESTAMP) (type: timestamp), CAST( cint AS TIMESTAMP) (type: timestamp), CAST( cbigint AS TIMESTAMP) (type: timestamp), CAST( cfloat AS TIMESTAMP) (type: timestamp), CAST( cdouble AS TIMESTAMP) (type: timestamp), CAST( cboolean1 AS TIMESTAMP) (type: timestamp), CAST( (cbigint * 0) AS TIMESTAMP) (type: timestamp), ctimestamp1 (type: timestamp), CAST( cstring1 AS TIMESTAMP) (type: timestamp), CAST( substr(cstring1, 1, 1) AS TIMESTAMP) (type: timestamp), UDFToString(ctinyint) (type: string), UDFToString(csmallint) (type: string), UDFToString(cint) (type: string), UDFToString(cbigint) (type: string), UDFToString(cfloat) (type: string), UDFToString(cdouble) (type: string), UDFToString(cboolean1) (type: string), UDFToString((cbigint * 0)) (type: string), UDFToString(ctimestamp1) (type: string), cstring1 (type: string), UDFToString(CAST( cstring1 AS CHAR(10)) (type: string), UDFToString(CAST( cstring1 AS varchar(10))) (type: string), UDFToFloat(UDFToInteger(cfloat)) (type: float), UDFToDouble((cint * 2)) (type: double), UDFToString(sin(cfloat)) (type: string), (UDFToDouble(UDFToFloat(cint)) + UDFToDouble(cboolean1)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40, _col41, _col42, _col43, _col44, _col45, _col46, _col47, _col48, _col49, _col50, _col51, _col52, _col53, _col54, _col55, _col56, _col57, _col58, _col59, _col60, _col61 + outputColumnNames: ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cboolean1, _o__c7, ctimestamp1, cstring1, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20, _o__c21, _o__c22, _o__c23, _o__c24, _o__c25, _o__c26, _o__c27, _o__c28, _o__c29, _o__c30, _o__c31, _o__c32, _o__c33, _o__c34, _o__c35, _o__c36, _o__c37, _o__c38, _o__c39, _o__c40, _o__c41, _o__c42, _o__c43, _o__c44, _o__c45, _o__c46, _o__c47, _o__c48, _o__c49, _o__c50, _o__c51, _o__c52, _o__c53, _o__c54, _o__c55, _o__c56, _o__c57, _o__c58, _o__c59, _o__c60, _o__c61 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vectorized_date_funcs.q.out b/ql/src/test/results/clientpositive/vectorized_date_funcs.q.out index 7f34905..7ae8ec0 100644 --- a/ql/src/test/results/clientpositive/vectorized_date_funcs.q.out +++ b/ql/src/test/results/clientpositive/vectorized_date_funcs.q.out @@ -244,7 +244,7 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: to_unix_timestamp(fl_time) (type: bigint), year(fl_time) (type: int), month(fl_time) (type: int), day(fl_time) (type: int), dayofmonth(fl_time) (type: int), weekofyear(fl_time) (type: int), CAST( fl_time AS DATE) (type: date), to_date(fl_time) (type: string), date_add(fl_time, 2) (type: string), date_sub(fl_time, 2) (type: string), datediff(fl_time, '2000-01-01') (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, fl_time, _o__c7, _o__c8, _o__c9, _o__c10 Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -471,7 +471,7 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: to_unix_timestamp(fl_date) (type: bigint), year(fl_date) (type: int), month(fl_date) (type: int), day(fl_date) (type: int), dayofmonth(fl_date) (type: int), weekofyear(fl_date) (type: int), fl_date (type: date), to_date(fl_date) (type: string), date_add(fl_date, 2) (type: string), date_sub(fl_date, 2) (type: string), datediff(fl_date, '2000-01-01') (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, fl_date, _o__c7, _o__c8, _o__c9, _o__c10 Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -696,7 +696,7 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (year(fl_time) = year(fl_date)) (type: boolean), (month(fl_time) = month(fl_date)) (type: boolean), (day(fl_time) = day(fl_date)) (type: boolean), (dayofmonth(fl_time) = dayofmonth(fl_date)) (type: boolean), (weekofyear(fl_time) = weekofyear(fl_date)) (type: boolean), (CAST( fl_time AS DATE) = fl_date) (type: boolean), (to_date(fl_time) = to_date(fl_date)) (type: boolean), (date_add(fl_time, 2) = date_add(fl_date, 2)) (type: boolean), (date_sub(fl_time, 2) = date_sub(fl_date, 2)) (type: boolean), (datediff(fl_time, '2000-01-01') = datediff(fl_date, '2000-01-01')) (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9 Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -913,7 +913,7 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_date (type: date), to_date(date_add(fl_date, 2)) (type: string), to_date(date_sub(fl_date, 2)) (type: string), datediff(fl_date, date_add(fl_date, 2)) (type: int), datediff(fl_date, date_sub(fl_date, 2)) (type: int), datediff(date_add(fl_date, 2), date_sub(fl_date, 2)) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: fl_date, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5 Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -1022,32 +1022,36 @@ STAGE PLANS: Group By Operator aggregations: min(VALUE._col0), max(VALUE._col1), count(VALUE._col2), count(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 256 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: date), $f1 (type: date), $f2 (type: bigint), $f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 256 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: date) + key expressions: $f0 (type: date) sort order: + - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: date), _col2 (type: bigint), _col3 (type: bigint) + Statistics: Num rows: 1 Data size: 256 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: date), $f2 (type: bigint), $f3 (type: bigint) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: date), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE + expressions: KEY.reducesinkkey0 (type: date), VALUE.$f1 (type: date), VALUE.$f2 (type: bigint), VALUE.$f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 256 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 256 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out b/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out index 2e041a3..d2a06c2 100644 --- a/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out +++ b/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out @@ -33,12 +33,12 @@ STAGE PLANS: Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int) - outputColumnNames: _col0 + outputColumnNames: a Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(DISTINCT _col0), count(DISTINCT _col0) + aggregations: sum(DISTINCT a), count(DISTINCT a) bucketGroup: true - keys: _col0 (type: int) + keys: a (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE @@ -51,15 +51,19 @@ STAGE PLANS: Group By Operator aggregations: sum(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint) + outputColumnNames: $f0, $f1 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -93,11 +97,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(DISTINCT _col0), count(DISTINCT _col0), avg(DISTINCT _col0), std(DISTINCT _col0) - keys: _col0 (type: int) + aggregations: sum(DISTINCT cint), count(DISTINCT cint), avg(DISTINCT cint), std(DISTINCT cint) + keys: cint (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -110,15 +114,19 @@ STAGE PLANS: Group By Operator aggregations: sum(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), avg(DISTINCT KEY._col0:2._col0), std(DISTINCT KEY._col0:3._col0) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: bigint), $f2 (type: double), $f3 (type: double) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vectorized_mapjoin.q.out b/ql/src/test/results/clientpositive/vectorized_mapjoin.q.out index f33ddcf..27083a2 100644 --- a/ql/src/test/results/clientpositive/vectorized_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/vectorized_mapjoin.q.out @@ -19,11 +19,11 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:t1 + t1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:t1 + t1 TableScan alias: t1 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -32,40 +32,40 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 cint (type: int) + 1 cint (type: int) Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: t2 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 + 0 cint (type: int) + 1 cint (type: int) + outputColumnNames: cint, cint0 Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: cint (type: int), cint0 (type: int), (cint + cint0) (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0), max(_col1), min(_col0), avg(_col2) + aggregations: count($f0), max($f1), min($f0), avg($f2) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -80,15 +80,19 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0), max(VALUE._col1), min(VALUE._col2), avg(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: int), $f2 (type: int), $f3 (type: double) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vectorized_math_funcs.q.out b/ql/src/test/results/clientpositive/vectorized_math_funcs.q.out index 29f80f6..6a278c2 100644 --- a/ql/src/test/results/clientpositive/vectorized_math_funcs.q.out +++ b/ql/src/test/results/clientpositive/vectorized_math_funcs.q.out @@ -122,7 +122,7 @@ STAGE PLANS: Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), round(cdouble, 2) (type: double), floor(cdouble) (type: bigint), ceil(cdouble) (type: bigint), rand() (type: double), rand(98007) (type: double), exp(ln(cdouble)) (type: double), ln(cdouble) (type: double), ln(cfloat) (type: double), log10(cdouble) (type: double), log2(cdouble) (type: double), log2((cdouble - 15601.0)) (type: double), log2(cfloat) (type: double), log2(cbigint) (type: double), log2(cint) (type: double), log2(csmallint) (type: double), log2(ctinyint) (type: double), log(2.0, cdouble) (type: double), power(log2(cdouble), 2.0) (type: double), power(log2(cdouble), 2.0) (type: double), sqrt(cdouble) (type: double), sqrt(cbigint) (type: double), bin(cbigint) (type: string), hex(cdouble) (type: string), conv(cbigint, 10, 16) (type: string), abs(cdouble) (type: double), abs(ctinyint) (type: int), (cint pmod 3) (type: int), sin(cdouble) (type: double), asin(cdouble) (type: double), cos(cdouble) (type: double), acos(cdouble) (type: double), atan(cdouble) (type: double), degrees(cdouble) (type: double), radians(cdouble) (type: double), cdouble (type: double), cbigint (type: bigint), (- cdouble) (type: double), sign(cdouble) (type: double), sign(cbigint) (type: double), cos(((- sin(log(cdouble))) + 3.14159)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40 + outputColumnNames: cdouble, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12, _o__c13, _o__c14, _o__c15, _o__c16, _o__c17, _o__c18, _o__c19, _o__c20, _o__c21, _o__c22, _o__c23, _o__c24, _o__c25, _o__c26, _o__c27, _o__c28, _o__c29, _o__c30, _o__c31, _o__c32, _o__c33, _o__c34, _o__c35, cbigint, _o__c37, _o__c38, _o__c39, _o__c40 Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out b/ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out index 82e90da..43e69cd 100644 --- a/ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out @@ -15,83 +15,79 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_0:v1 + t1:v2 Fetch Operator limit: -1 - $hdt$_0:$hdt$_1:v1 + v3 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_0:v1 + t1:v2 TableScan - alias: v1 + alias: t1:v2 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ctinyint is not null and csmallint is not null) (type: boolean) - Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ctinyint (type: tinyint), csmallint (type: smallint), cdouble (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) - $hdt$_0:$hdt$_1:v1 + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: ctinyint + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) + v3 TableScan - alias: v1 + alias: v3 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: csmallint is not null (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint) - outputColumnNames: _col0 + outputColumnNames: csmallint Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: smallint) - 1 _col0 (type: smallint) + 0 csmallint (type: smallint) + 1 csmallint (type: smallint) Stage: Stage-3 Map Reduce Map Operator Tree: TableScan - alias: v1 + alias: t1:v1 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ctinyint is not null (type: boolean) + predicate: csmallint is not null (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cdouble (type: double) + outputColumnNames: ctinyint, csmallint, cdouble Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: tinyint) - 1 _col0 (type: tinyint) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: smallint), _col2 (type: double) - outputColumnNames: _col0, _col1 + 0 ctinyint (type: tinyint) + 1 ctinyint (type: tinyint) + outputColumnNames: csmallint, cdouble + Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: csmallint is not null (type: boolean) Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: smallint) - 1 _col0 (type: smallint) - outputColumnNames: _col1 + 0 csmallint (type: smallint) + 1 csmallint (type: smallint) + outputColumnNames: cdouble Statistics: Num rows: 7433 Data size: 1598388 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: double) - outputColumnNames: _col0 + expressions: cdouble (type: double) + outputColumnNames: $f0 Statistics: Num rows: 7433 Data size: 1598388 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum($f0) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -106,15 +102,19 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: double) + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -130,4 +130,4 @@ POSTHOOK: query: select sum(t1.td) from (select v1.csmallint as tsi, v1.cdouble POSTHOOK: type: QUERY POSTHOOK: Input: default@alltypesorc #### A masked pattern was here #### -6.065190932486892E11 +6.065190932488167E11 diff --git a/ql/src/test/results/clientpositive/vectorized_parquet.q.out b/ql/src/test/results/clientpositive/vectorized_parquet.q.out index 7b2dc6d..64d4508 100644 --- a/ql/src/test/results/clientpositive/vectorized_parquet.q.out +++ b/ql/src/test/results/clientpositive/vectorized_parquet.q.out @@ -72,7 +72,7 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 36864 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 528534767 (type: int), ctinyint (type: tinyint), csmallint (type: smallint), cfloat (type: float), cdouble (type: double), cstring1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: cint, ctinyint, csmallint, cfloat, cdouble, cstring1 Statistics: Num rows: 6144 Data size: 36864 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 @@ -146,11 +146,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 73728 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cint (type: int), csmallint (type: smallint), cstring1 (type: string), cfloat (type: float), cdouble (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5 Statistics: Num rows: 12288 Data size: 73728 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), min(_col2), count(_col3), avg(_col4), stddev_pop(_col5) - keys: _col0 (type: tinyint) + aggregations: max($f1), min($f2), count($f3), avg($f4), stddev_pop($f5) + keys: $f0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 12288 Data size: 73728 Basic stats: COMPLETE Column stats: NONE @@ -165,15 +165,19 @@ STAGE PLANS: aggregations: max(VALUE._col0), min(VALUE._col1), count(VALUE._col2), avg(VALUE._col3), stddev_pop(VALUE._col4) keys: KEY._col0 (type: tinyint) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5 Statistics: Num rows: 6144 Data size: 36864 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: $f0 (type: tinyint), $f1 (type: int), $f2 (type: smallint), $f3 (type: bigint), $f4 (type: double), $f5 (type: double) + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5 Statistics: Num rows: 6144 Data size: 36864 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 6144 Data size: 36864 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vectorized_parquet_types.q.out b/ql/src/test/results/clientpositive/vectorized_parquet_types.q.out index 8d1bddc..c18b22e 100644 --- a/ql/src/test/results/clientpositive/vectorized_parquet_types.q.out +++ b/ql/src/test/results/clientpositive/vectorized_parquet_types.q.out @@ -140,7 +140,7 @@ STAGE PLANS: Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), ctinyint (type: tinyint), csmallint (type: smallint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), t (type: timestamp), cchar (type: char(5)), cvarchar (type: varchar(10)), hex(cbinary) (type: string), cdecimal (type: decimal(4,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: cint, ctinyint, csmallint, cfloat, cdouble, cstring1, t, cchar, cvarchar, _o__c9, cdecimal Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -207,7 +207,7 @@ STAGE PLANS: Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cchar (type: char(5)), length(cchar) (type: int), cvarchar (type: varchar(10)), length(cvarchar) (type: int), cdecimal (type: decimal(4,2)), sign(cdecimal) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: cchar, _o__c1, cvarchar, _o__c3, cdecimal, _o__c5 Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -291,11 +291,11 @@ STAGE PLANS: Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cint (type: int), csmallint (type: smallint), cstring1 (type: string), cfloat (type: float), cdouble (type: double), cdecimal (type: decimal(4,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6 Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), min(_col2), count(_col3), avg(_col4), stddev_pop(_col5), max(_col6) - keys: _col0 (type: tinyint) + aggregations: max($f1), min($f2), count($f3), avg($f4), stddev_pop($f5), max($f6) + keys: $f0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE @@ -310,28 +310,32 @@ STAGE PLANS: aggregations: max(VALUE._col0), min(VALUE._col1), count(VALUE._col2), avg(VALUE._col3), stddev_pop(VALUE._col4), max(VALUE._col5) keys: KEY._col0 (type: tinyint) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6 Statistics: Num rows: 11 Data size: 121 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: $f0 (type: tinyint), $f1 (type: int), $f2 (type: smallint), $f3 (type: bigint), $f4 (type: double), $f5 (type: double), $f6 (type: decimal(4,2)) + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6 + Statistics: Num rows: 11 Data size: 121 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: tinyint) + key expressions: $f0 (type: tinyint) sort order: + Statistics: Num rows: 11 Data size: 121 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: smallint), _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: decimal(4,2)) + value expressions: $f1 (type: int), $f2 (type: smallint), $f3 (type: bigint), $f4 (type: double), $f5 (type: double), $f6 (type: decimal(4,2)) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: tinyint), VALUE._col0 (type: int), VALUE._col1 (type: smallint), VALUE._col2 (type: bigint), VALUE._col3 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: decimal(4,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + expressions: KEY.reducesinkkey0 (type: tinyint), VALUE.$f1 (type: int), VALUE.$f2 (type: smallint), VALUE.$f3 (type: bigint), VALUE.$f4 (type: double), VALUE.$f5 (type: double), VALUE.$f6 (type: decimal(4,2)) + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6 Statistics: Num rows: 11 Data size: 121 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vectorized_ptf.q.out b/ql/src/test/results/clientpositive/vectorized_ptf.q.out index e65a880..f8557ec 100644 --- a/ql/src/test/results/clientpositive/vectorized_ptf.q.out +++ b/ql/src/test/results/clientpositive/vectorized_ptf.q.out @@ -263,7 +263,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -283,7 +283,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -654,7 +654,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -674,7 +674,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -691,23 +691,27 @@ STAGE PLANS: 1 p_partkey (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + Select Operator + expressions: _col1 (type: string), _col2 (type: string), _col5 (type: int) + outputColumnNames: _col1, _col2, _col5 + Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col1,_col2,_col5 - columns.types string,string,int - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col1,_col2,_col5 + columns.types string,string,int + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -1017,7 +1021,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1037,7 +1041,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -1283,7 +1287,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1303,7 +1307,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -1657,7 +1661,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -1677,7 +1681,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -2041,7 +2045,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -2061,7 +2065,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -2160,66 +2164,70 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string, _col2: int - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col1 - partition by: _col0 - raw input shape: - window functions: - window function definition - alias: rank_window_0 - arguments: _col1 - name: rank - window function: GenericUDAFRankEvaluator - window frame: PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true - window function definition - alias: dense_rank_window_1 - arguments: _col1 - name: dense_rank - window function: GenericUDAFDenseRankEvaluator - window frame: PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true - window function definition - alias: lag_window_2 - arguments: _col2, 1, _col2 - name: lag - window function: GenericUDAFLagEvaluator - window frame: PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), _col2 (type: int), (_col2 - lag_window_2) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string, _col2: int + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col1 + partition by: _col0 + raw input shape: + window functions: + window function definition + alias: rank_window_0 + arguments: _col1 + name: rank + window function: GenericUDAFRankEvaluator + window frame: PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true + window function definition + alias: dense_rank_window_1 + arguments: _col1 + name: dense_rank + window function: GenericUDAFDenseRankEvaluator + window frame: PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true + window function definition + alias: lag_window_2 + arguments: _col2, 1, _col2 + name: lag + window function: GenericUDAFLagEvaluator + window frame: PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), _col2 (type: int), (_col2 - lag_window_2) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6 - columns.types string:string:int:int:int:int:int - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6 + columns.types string:string:int:int:int:int:int + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -2380,7 +2388,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -2400,7 +2408,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -2520,7 +2528,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -2540,7 +2548,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -2558,27 +2566,31 @@ STAGE PLANS: 1 p_partkey (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8 - columns.types int:string:string:string:string:int:string:double:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8 + columns.types int:string:string:string:string:int:string:double:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -2734,7 +2746,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -2754,7 +2766,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -2874,7 +2886,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -2894,7 +2906,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -3116,7 +3128,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -3136,7 +3148,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -3479,7 +3491,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -3499,7 +3511,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -3844,7 +3856,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -3864,7 +3876,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -4219,7 +4231,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -4239,7 +4251,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -4721,7 +4733,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -4741,7 +4753,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -5185,7 +5197,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -5205,7 +5217,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -5325,7 +5337,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -5345,7 +5357,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -5650,7 +5662,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -5670,7 +5682,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -5769,27 +5781,31 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types string:string:int - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types string:string:int + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -5982,7 +5998,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -6002,7 +6018,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -6018,37 +6034,41 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: mfgr_price_view - output shape: _col0: string, _col1: string, _col2: double - type: TABLE - Partition table definition - input alias: ptf_1 - name: noop - order by: _col0 - output shape: _col0: string, _col1: string, _col2: double - partition by: _col0 - raw input shape: + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: double) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + PTF Operator + Function definitions: + Input definition + input alias: mfgr_price_view + output shape: _col0: string, _col1: string, _col2: double + type: TABLE + Partition table definition + input alias: ptf_1 + name: noop + order by: _col0 + output shape: _col0: string, _col1: string, _col2: double + partition by: _col0 + raw input shape: + Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types string,string,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types string,string,double + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -6501,7 +6521,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -6521,7 +6541,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -7251,7 +7271,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -7271,7 +7291,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -7791,7 +7811,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -7811,7 +7831,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -8359,7 +8379,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -8379,7 +8399,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -8870,7 +8890,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -8890,7 +8910,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -9498,7 +9518,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -9518,7 +9538,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc @@ -10023,7 +10043,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -10043,7 +10063,7 @@ STAGE PLANS: serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 2639 + totalSize 2689 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc diff --git a/ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out b/ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out index f32cc38..476faae 100644 --- a/ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out +++ b/ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out @@ -28,43 +28,43 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: cint (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: cint (type: int) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE TableScan - alias: t1 + alias: t2 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: cint (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: cint (type: int) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 + 0 cint (type: int) + 1 cint (type: int) + outputColumnNames: cint, cint0 Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: cint (type: int), cint0 (type: int), (cint + cint0) (type: int) + outputColumnNames: $f0, $f1, $f2 Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0), max(_col1), min(_col0), avg(_col2) + aggregations: count($f0), max($f1), min($f0), avg($f2) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -87,32 +87,36 @@ STAGE PLANS: Group By Operator aggregations: count(VALUE._col0), max(VALUE._col1), min(VALUE._col2), avg(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f1 (type: int), $f2 (type: int), $f3 (type: double) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: bigint) + key expressions: $f0 (type: bigint) sort order: + - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: double) + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + value expressions: $f1 (type: int), $f2 (type: int), $f3 (type: double) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: bigint), VALUE._col0 (type: int), VALUE._col1 (type: int), VALUE._col2 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + expressions: KEY.reducesinkkey0 (type: bigint), VALUE.$f1 (type: int), VALUE.$f2 (type: int), VALUE.$f3 (type: double) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorized_string_funcs.q.out b/ql/src/test/results/clientpositive/vectorized_string_funcs.q.out index 8a5925e..a82eb29 100644 --- a/ql/src/test/results/clientpositive/vectorized_string_funcs.q.out +++ b/ql/src/test/results/clientpositive/vectorized_string_funcs.q.out @@ -62,7 +62,7 @@ STAGE PLANS: Statistics: Num rows: 1024 Data size: 220163 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(cstring1, 1, 2) (type: string), substr(cstring1, 2) (type: string), lower(cstring1) (type: string), upper(cstring1) (type: string), upper(cstring1) (type: string), length(cstring1) (type: int), trim(cstring1) (type: string), ltrim(cstring1) (type: string), rtrim(cstring1) (type: string), concat(cstring1, cstring2) (type: string), concat('>', cstring1) (type: string), concat(cstring1, '<') (type: string), concat(substr(cstring1, 1, 2), substr(cstring2, 1, 2)) (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8, _o__c9, _o__c10, _o__c11, _o__c12 Statistics: Num rows: 1024 Data size: 220163 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vectorized_timestamp_funcs.q.out b/ql/src/test/results/clientpositive/vectorized_timestamp_funcs.q.out index f66903b..7d3f56b 100644 --- a/ql/src/test/results/clientpositive/vectorized_timestamp_funcs.q.out +++ b/ql/src/test/results/clientpositive/vectorized_timestamp_funcs.q.out @@ -112,18 +112,18 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: to_unix_timestamp(ctimestamp1) (type: bigint), year(ctimestamp1) (type: int), month(ctimestamp1) (type: int), day(ctimestamp1) (type: int), dayofmonth(ctimestamp1) (type: int), weekofyear(ctimestamp1) (type: int), hour(ctimestamp1) (type: int), minute(ctimestamp1) (type: int), second(ctimestamp1) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: c1, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: bigint) + key expressions: c1 (type: bigint) sort order: + Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: int), _col8 (type: int) + value expressions: _o__c1 (type: int), _o__c2 (type: int), _o__c3 (type: int), _o__c4 (type: int), _o__c5 (type: int), _o__c6 (type: int), _o__c7 (type: int), _o__c8 (type: int) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: bigint), VALUE._col0 (type: int), VALUE._col1 (type: int), VALUE._col2 (type: int), VALUE._col3 (type: int), VALUE._col4 (type: int), VALUE._col5 (type: int), VALUE._col6 (type: int), VALUE._col7 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + expressions: KEY.reducesinkkey0 (type: bigint), VALUE._o__c1 (type: int), VALUE._o__c2 (type: int), VALUE._o__c3 (type: int), VALUE._o__c4 (type: int), VALUE._o__c5 (type: int), VALUE._o__c6 (type: int), VALUE._o__c7 (type: int), VALUE._o__c8 (type: int) + outputColumnNames: c1, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -248,18 +248,18 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: to_unix_timestamp(stimestamp1) (type: bigint), year(stimestamp1) (type: int), month(stimestamp1) (type: int), day(stimestamp1) (type: int), dayofmonth(stimestamp1) (type: int), weekofyear(stimestamp1) (type: int), hour(stimestamp1) (type: int), minute(stimestamp1) (type: int), second(stimestamp1) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: c1, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: bigint) + key expressions: c1 (type: bigint) sort order: + Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: int), _col8 (type: int) + value expressions: _o__c1 (type: int), _o__c2 (type: int), _o__c3 (type: int), _o__c4 (type: int), _o__c5 (type: int), _o__c6 (type: int), _o__c7 (type: int), _o__c8 (type: int) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: bigint), VALUE._col0 (type: int), VALUE._col1 (type: int), VALUE._col2 (type: int), VALUE._col3 (type: int), VALUE._col4 (type: int), VALUE._col5 (type: int), VALUE._col6 (type: int), VALUE._col7 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + expressions: KEY.reducesinkkey0 (type: bigint), VALUE._o__c1 (type: int), VALUE._o__c2 (type: int), VALUE._o__c3 (type: int), VALUE._o__c4 (type: int), VALUE._o__c5 (type: int), VALUE._o__c6 (type: int), VALUE._o__c7 (type: int), VALUE._o__c8 (type: int) + outputColumnNames: c1, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -384,18 +384,18 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (to_unix_timestamp(ctimestamp1) = to_unix_timestamp(stimestamp1)) (type: boolean), (year(ctimestamp1) = year(stimestamp1)) (type: boolean), (month(ctimestamp1) = month(stimestamp1)) (type: boolean), (day(ctimestamp1) = day(stimestamp1)) (type: boolean), (dayofmonth(ctimestamp1) = dayofmonth(stimestamp1)) (type: boolean), (weekofyear(ctimestamp1) = weekofyear(stimestamp1)) (type: boolean), (hour(ctimestamp1) = hour(stimestamp1)) (type: boolean), (minute(ctimestamp1) = minute(stimestamp1)) (type: boolean), (second(ctimestamp1) = second(stimestamp1)) (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: c1, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: boolean) + key expressions: c1 (type: boolean) sort order: + Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean) + value expressions: _o__c1 (type: boolean), _o__c2 (type: boolean), _o__c3 (type: boolean), _o__c4 (type: boolean), _o__c5 (type: boolean), _o__c6 (type: boolean), _o__c7 (type: boolean), _o__c8 (type: boolean) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: boolean), VALUE._col0 (type: boolean), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean), VALUE._col3 (type: boolean), VALUE._col4 (type: boolean), VALUE._col5 (type: boolean), VALUE._col6 (type: boolean), VALUE._col7 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + expressions: KEY.reducesinkkey0 (type: boolean), VALUE._o__c1 (type: boolean), VALUE._o__c2 (type: boolean), VALUE._o__c3 (type: boolean), VALUE._o__c4 (type: boolean), VALUE._o__c5 (type: boolean), VALUE._o__c6 (type: boolean), VALUE._o__c7 (type: boolean), VALUE._o__c8 (type: boolean) + outputColumnNames: c1, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -524,18 +524,18 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: to_unix_timestamp(stimestamp1) (type: bigint), year(stimestamp1) (type: int), month(stimestamp1) (type: int), day(stimestamp1) (type: int), dayofmonth(stimestamp1) (type: int), weekofyear(stimestamp1) (type: int), hour(stimestamp1) (type: int), minute(stimestamp1) (type: int), second(stimestamp1) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: c1, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8 Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: bigint) + key expressions: c1 (type: bigint) sort order: + Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: int), _col8 (type: int) + value expressions: _o__c1 (type: int), _o__c2 (type: int), _o__c3 (type: int), _o__c4 (type: int), _o__c5 (type: int), _o__c6 (type: int), _o__c7 (type: int), _o__c8 (type: int) Execution mode: vectorized Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: bigint), VALUE._col0 (type: int), VALUE._col1 (type: int), VALUE._col2 (type: int), VALUE._col3 (type: int), VALUE._col4 (type: int), VALUE._col5 (type: int), VALUE._col6 (type: int), VALUE._col7 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + expressions: KEY.reducesinkkey0 (type: bigint), VALUE._o__c1 (type: int), VALUE._o__c2 (type: int), VALUE._o__c3 (type: int), VALUE._o__c4 (type: int), VALUE._o__c5 (type: int), VALUE._o__c6 (type: int), VALUE._o__c7 (type: int), VALUE._o__c8 (type: int) + outputColumnNames: c1, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7, _o__c8 Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -611,10 +611,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ctimestamp1 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0), max(_col0), count(_col0), count() + aggregations: min(ctimestamp1), max(ctimestamp1), count(ctimestamp1), count() mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE @@ -627,15 +627,19 @@ STAGE PLANS: Group By Operator aggregations: min(VALUE._col0), max(VALUE._col1), count(VALUE._col2), count(VALUE._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: timestamp), $f1 (type: timestamp), $f2 (type: bigint), $f3 (type: bigint) + outputColumnNames: $f0, $f1, $f2, $f3 + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -685,10 +689,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ctimestamp1 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(ctimestamp1) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -700,15 +704,15 @@ STAGE PLANS: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: $f0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: round(_col0, 3) (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + expressions: round($f0, 3) (type: double) + outputColumnNames: _o__c0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -768,10 +772,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ctimestamp1 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), variance(_col0), var_pop(_col0), var_samp(_col0), std(_col0), stddev(_col0), stddev_pop(_col0), stddev_samp(_col0) + aggregations: avg(ctimestamp1), variance(ctimestamp1), var_pop(ctimestamp1), var_samp(ctimestamp1), std(ctimestamp1), stddev(ctimestamp1), stddev_pop(ctimestamp1), stddev_samp(ctimestamp1) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -784,11 +788,11 @@ STAGE PLANS: Group By Operator aggregations: avg(VALUE._col0), variance(VALUE._col1), var_pop(VALUE._col2), var_samp(VALUE._col3), std(VALUE._col4), stddev(VALUE._col5), stddev_pop(VALUE._col6), stddev_samp(VALUE._col7) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7 Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: round(_col0, 0) (type: double), _col1 BETWEEN 8.97077295279421E19 AND 8.97077295279422E19 (type: boolean), _col2 BETWEEN 8.97077295279421E19 AND 8.97077295279422E19 (type: boolean), _col3 BETWEEN 9.20684592523616E19 AND 9.20684592523617E19 (type: boolean), round(_col4, 3) (type: double), round(_col5, 3) (type: double), round(_col6, 3) (type: double), round(_col7, 3) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + expressions: round($f0, 0) (type: double), $f1 BETWEEN 8.97077295279421E19 AND 8.97077295279422E19 (type: boolean), $f2 BETWEEN 8.97077295279421E19 AND 8.97077295279422E19 (type: boolean), $f3 BETWEEN 9.20684592523616E19 AND 9.20684592523617E19 (type: boolean), round($f4, 3) (type: double), round($f5, 3) (type: double), round($f6, 3) (type: double), round($f7, 3) (type: double) + outputColumnNames: _o__c0, _o__c1, _o__c2, _o__c3, _o__c4, _o__c5, _o__c6, _o__c7 Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/vectorized_timestamp_ints_casts.q.out b/ql/src/test/results/clientpositive/vectorized_timestamp_ints_casts.q.out index 7ca0ee4..9c0ae9d 100644 --- a/ql/src/test/results/clientpositive/vectorized_timestamp_ints_casts.q.out +++ b/ql/src/test/results/clientpositive/vectorized_timestamp_ints_casts.q.out @@ -50,7 +50,7 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CAST( ctinyint AS TIMESTAMP) (type: timestamp), CAST( csmallint AS TIMESTAMP) (type: timestamp), CAST( cint AS TIMESTAMP) (type: timestamp), CAST( cbigint AS TIMESTAMP) (type: timestamp), CAST( cfloat AS TIMESTAMP) (type: timestamp), CAST( cdouble AS TIMESTAMP) (type: timestamp), CAST( cboolean1 AS TIMESTAMP) (type: timestamp), CAST( (cbigint * 0) AS TIMESTAMP) (type: timestamp), ctimestamp1 (type: timestamp), CAST( cstring1 AS TIMESTAMP) (type: timestamp), CAST( substr(cstring1, 1, 1) AS TIMESTAMP) (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cboolean1, _o__c7, ctimestamp1, cstring1, _o__c10 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -183,7 +183,7 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CAST( ctinyint AS TIMESTAMP) (type: timestamp), CAST( csmallint AS TIMESTAMP) (type: timestamp), CAST( cint AS TIMESTAMP) (type: timestamp), CAST( cbigint AS TIMESTAMP) (type: timestamp), CAST( cfloat AS TIMESTAMP) (type: timestamp), CAST( cdouble AS TIMESTAMP) (type: timestamp), CAST( cboolean1 AS TIMESTAMP) (type: timestamp), CAST( (cbigint * 0) AS TIMESTAMP) (type: timestamp), ctimestamp1 (type: timestamp), CAST( cstring1 AS TIMESTAMP) (type: timestamp), CAST( substr(cstring1, 1, 1) AS TIMESTAMP) (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cboolean1, _o__c7, ctimestamp1, cstring1, _o__c10 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -238,29 +238,29 @@ where cbigint % 250 = 0 POSTHOOK: type: QUERY POSTHOOK: Input: default@alltypesorc #### A masked pattern was here #### -1969-12-31 15:59:24 1969-12-31 15:56:40 NULL 1906-06-05 13:34:10 1969-12-31 15:59:24 1969-12-31 15:56:40 NULL 1969-12-31 16:00:00 1969-12-31 15:59:45.748 NULL NULL -1969-12-31 15:59:24 1969-12-31 15:56:40 NULL 2020-09-11 19:50:00 1969-12-31 15:59:24 1969-12-31 15:56:40 NULL 1969-12-31 16:00:00 1969-12-31 15:59:53.817 NULL NULL -1969-12-31 15:59:30 1969-12-31 15:56:40 NULL 2015-04-23 22:10:50 1969-12-31 15:59:30 1969-12-31 15:56:40 NULL 1969-12-31 16:00:00 1969-12-31 16:00:12.935 NULL NULL -1969-12-31 15:59:09 NULL 1994-07-07 10:09:31 2003-05-25 21:27:30 1969-12-31 15:59:09 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:08.451 NULL NULL -1969-12-31 15:59:09 NULL 1993-09-08 22:51:22 1908-10-29 07:05:50 1969-12-31 15:59:09 NULL 1969-12-31 16:00:01 1969-12-31 16:00:00 1969-12-31 16:00:08.451 NULL NULL -1969-12-31 16:00:20 1969-12-31 20:20:01 NULL 1958-07-07 21:05:50 1969-12-31 16:00:20 1969-12-31 20:20:01 NULL 1969-12-31 16:00:00 1969-12-31 15:59:45.129 NULL NULL -1969-12-31 15:59:22 1969-12-31 20:20:01 NULL 1911-02-07 01:30:00 1969-12-31 15:59:22 1969-12-31 20:20:01 NULL 1969-12-31 16:00:00 1969-12-31 15:59:58.614 NULL NULL -1969-12-31 15:59:55 1969-12-31 20:20:01 NULL 1989-05-28 20:33:20 1969-12-31 15:59:55 1969-12-31 20:20:01 NULL 1969-12-31 16:00:00 1969-12-31 16:00:04.679 NULL NULL -1969-12-31 16:00:48 1969-12-31 20:20:01 NULL 1944-10-18 03:23:20 1969-12-31 16:00:48 1969-12-31 20:20:01 NULL 1969-12-31 16:00:00 1969-12-31 15:59:50.235 NULL NULL -1969-12-31 16:00:08 NULL 1949-01-13 00:21:02 1940-06-26 15:47:30 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL -1969-12-31 16:00:08 NULL 1966-09-27 07:32:46 1928-05-26 10:07:30 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL -1969-12-31 16:00:08 NULL 1995-07-07 22:01:04 1997-07-05 20:58:20 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL -1969-12-31 16:00:08 NULL 1948-10-12 08:01:29 2020-05-04 04:20:50 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL -1969-12-31 16:00:08 NULL 1998-03-27 00:56:12 1910-12-27 06:10:00 1969-12-31 16:00:08 NULL 1969-12-31 16:00:01 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL -1969-12-31 16:00:08 NULL 1999-07-01 15:14:06 2008-03-13 02:07:30 1969-12-31 16:00:08 NULL 1969-12-31 16:00:01 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL -1969-12-31 15:59:01 1969-12-31 14:00:04 NULL 1919-02-22 13:13:20 1969-12-31 15:59:01 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:13.15 NULL NULL -1969-12-31 15:59:39 1969-12-31 14:00:04 NULL 2018-11-16 20:30:00 1969-12-31 15:59:39 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 15:59:55.9 NULL NULL -1969-12-31 15:59:00 1969-12-31 14:00:04 NULL 2018-01-18 14:32:30 1969-12-31 15:59:00 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 15:59:52.408 NULL NULL -1969-12-31 15:59:46 1969-12-31 14:00:04 NULL 1920-10-24 09:28:20 1969-12-31 15:59:46 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:11.065 NULL NULL -1969-12-31 16:00:59 1969-12-31 14:00:04 NULL 1933-12-12 05:05:00 1969-12-31 16:00:59 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:10.956 NULL NULL -1969-12-31 15:59:52 1969-12-31 14:00:04 NULL 1911-05-18 17:28:20 1969-12-31 15:59:52 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:03.136 NULL NULL -1969-12-31 16:00:05 1969-12-31 14:00:04 NULL 1937-10-25 22:48:20 1969-12-31 16:00:05 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:10.973 NULL NULL -1969-12-31 15:59:36 1969-12-31 14:00:04 NULL 1996-04-09 21:36:40 1969-12-31 15:59:36 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 15:59:53.145 NULL NULL -1969-12-31 15:59:10 1969-12-31 14:00:04 NULL 1937-04-28 15:05:50 1969-12-31 15:59:10 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 15:59:54.733 NULL NULL -1969-12-31 16:00:11 NULL 1967-12-14 19:06:58 2027-02-19 08:15:50 1969-12-31 16:00:11 NULL 1969-12-31 16:00:01 1969-12-31 16:00:00 1969-12-31 16:00:02.351 NULL NULL -1969-12-31 16:00:11 NULL 1959-05-16 04:19:43 2009-01-30 06:50:00 1969-12-31 16:00:11 NULL 1969-12-31 16:00:01 1969-12-31 16:00:00 1969-12-31 16:00:02.351 NULL NULL +1969-12-31 15:59:59.964 1969-12-31 15:59:59.8 NULL 1969-12-08 10:43:03.25 1969-12-31 15:59:24 1969-12-31 15:56:40 NULL 1969-12-31 16:00:00 1969-12-31 15:59:45.748 NULL NULL +1969-12-31 15:59:59.964 1969-12-31 15:59:59.8 NULL 1970-01-19 04:24:39 1969-12-31 15:59:24 1969-12-31 15:56:40 NULL 1969-12-31 16:00:00 1969-12-31 15:59:53.817 NULL NULL +1969-12-31 15:59:59.97 1969-12-31 15:59:59.8 NULL 1970-01-17 05:10:52.25 1969-12-31 15:59:30 1969-12-31 15:56:40 NULL 1969-12-31 16:00:00 1969-12-31 16:00:12.935 NULL NULL +1969-12-31 15:59:59.949 NULL 1970-01-09 14:53:20.971 1970-01-12 20:45:23.25 1969-12-31 15:59:09 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:08.451 NULL NULL +1969-12-31 15:59:59.949 NULL 1970-01-09 07:39:13.882 1969-12-09 07:45:32.75 1969-12-31 15:59:09 NULL 1969-12-31 16:00:00.001 1969-12-31 16:00:00 1969-12-31 16:00:08.451 NULL NULL +1969-12-31 16:00:00.02 1969-12-31 16:00:15.601 NULL 1969-12-27 11:19:26.75 1969-12-31 16:00:20 1969-12-31 20:20:01 NULL 1969-12-31 16:00:00 1969-12-31 15:59:45.129 NULL NULL +1969-12-31 15:59:59.962 1969-12-31 16:00:15.601 NULL 1969-12-10 03:41:51 1969-12-31 15:59:22 1969-12-31 20:20:01 NULL 1969-12-31 16:00:00 1969-12-31 15:59:58.614 NULL NULL +1969-12-31 15:59:59.995 1969-12-31 16:00:15.601 NULL 1970-01-07 18:06:56 1969-12-31 15:59:55 1969-12-31 20:20:01 NULL 1969-12-31 16:00:00 1969-12-31 16:00:04.679 NULL NULL +1969-12-31 16:00:00.048 1969-12-31 16:00:15.601 NULL 1969-12-22 11:03:59 1969-12-31 16:00:48 1969-12-31 20:20:01 NULL 1969-12-31 16:00:00 1969-12-31 15:59:50.235 NULL NULL +1969-12-31 16:00:00.008 NULL 1969-12-24 00:12:58.862 1969-12-20 21:16:47.25 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL +1969-12-31 16:00:00.008 NULL 1969-12-30 11:24:23.566 1969-12-16 11:20:17.25 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL +1969-12-31 16:00:00.008 NULL 1970-01-09 23:39:39.664 1970-01-10 17:09:21.5 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL +1969-12-31 16:00:00.008 NULL 1969-12-23 21:59:27.689 1970-01-19 01:16:31.25 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL +1969-12-31 16:00:00.008 NULL 1970-01-10 23:29:48.972 1969-12-10 02:41:39 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00.001 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL +1969-12-31 16:00:00.008 NULL 1970-01-11 10:34:27.246 1970-01-14 14:49:59.25 1969-12-31 16:00:08 NULL 1969-12-31 16:00:00.001 1969-12-31 16:00:00 1969-12-31 16:00:15.892 NULL NULL +1969-12-31 15:59:59.941 1969-12-31 15:59:52.804 NULL 1969-12-13 02:11:50 1969-12-31 15:59:01 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:13.15 NULL NULL +1969-12-31 15:59:59.979 1969-12-31 15:59:52.804 NULL 1970-01-18 12:27:09 1969-12-31 15:59:39 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 15:59:55.9 NULL NULL +1969-12-31 15:59:59.94 1969-12-31 15:59:52.804 NULL 1970-01-18 05:11:54.75 1969-12-31 15:59:00 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 15:59:52.408 NULL NULL +1969-12-31 15:59:59.986 1969-12-31 15:59:52.804 NULL 1969-12-13 16:50:00.5 1969-12-31 15:59:46 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:11.065 NULL NULL +1969-12-31 16:00:00.059 1969-12-31 15:59:52.804 NULL 1969-12-18 11:57:25.5 1969-12-31 16:00:59 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:10.956 NULL NULL +1969-12-31 15:59:59.992 1969-12-31 15:59:52.804 NULL 1969-12-10 06:06:48.5 1969-12-31 15:59:52 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:03.136 NULL NULL +1969-12-31 16:00:00.005 1969-12-31 15:59:52.804 NULL 1969-12-19 21:53:12.5 1969-12-31 16:00:05 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 16:00:10.973 NULL NULL +1969-12-31 15:59:59.976 1969-12-31 15:59:52.804 NULL 1970-01-10 06:18:31 1969-12-31 15:59:36 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 15:59:53.145 NULL NULL +1969-12-31 15:59:59.95 1969-12-31 15:59:52.804 NULL 1969-12-19 17:33:32.75 1969-12-31 15:59:10 1969-12-31 14:00:04 NULL 1969-12-31 16:00:00 1969-12-31 15:59:54.733 NULL NULL +1969-12-31 16:00:00.011 NULL 1969-12-30 22:03:04.018 1970-01-21 12:50:53.75 1969-12-31 16:00:11 NULL 1969-12-31 16:00:00.001 1969-12-31 16:00:00 1969-12-31 16:00:02.351 NULL NULL +1969-12-31 16:00:00.011 NULL 1969-12-27 18:49:09.583 1970-01-14 22:35:27 1969-12-31 16:00:11 NULL 1969-12-31 16:00:00.001 1969-12-31 16:00:00 1969-12-31 16:00:02.351 NULL NULL diff --git a/ql/src/test/results/clientpositive/windowing.q.out b/ql/src/test/results/clientpositive/windowing.q.out index b17bfc1..aa34d3d 100644 --- a/ql/src/test/results/clientpositive/windowing.q.out +++ b/ql/src/test/results/clientpositive/windowing.q.out @@ -659,32 +659,32 @@ window w1 as (distribute by p_mfgr sort by p_mfgr, p_name rows between 2 precedi POSTHOOK: type: QUERY POSTHOOK: Input: default@part #### A masked pattern was here #### -Manufacturer#1 almond antique burnished rose metallic 2 1 1 0.3333333333333333 0.0 1 2 2.0 0.0 2 2 2 -Manufacturer#1 almond antique burnished rose metallic 2 1 1 0.3333333333333333 0.0 1 2 2.0 0.0 2 2 2 -Manufacturer#1 almond antique chartreuse lavender yellow 34 3 2 0.5 0.4 2 3 12.666666666666666 15.084944665313014 2 34 2 -Manufacturer#1 almond antique salmon chartreuse burlywood 6 4 3 0.6666666666666666 0.6 2 4 11.0 13.379088160259652 2 6 2 -Manufacturer#1 almond aquamarine burnished black steel 28 5 4 0.8333333333333334 0.8 3 5 14.4 13.763720427268202 2 28 34 -Manufacturer#1 almond aquamarine pink moccasin thistle 42 6 5 1.0 1.0 3 6 19.0 16.237815945091466 2 42 6 -Manufacturer#2 almond antique violet chocolate turquoise 14 1 1 0.2 0.0 1 1 14.0 0.0 4 14 14 -Manufacturer#2 almond antique violet turquoise frosted 40 2 2 0.4 0.25 1 2 27.0 13.0 4 40 14 -Manufacturer#2 almond aquamarine midnight light salmon 2 3 3 0.6 0.5 2 3 18.666666666666668 15.86050300449376 4 2 14 -Manufacturer#2 almond aquamarine rose maroon antique 25 4 4 0.8 0.75 2 4 20.25 14.00669482783144 4 25 40 -Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 5 5 1.0 1.0 3 5 19.8 12.560254774486067 4 18 2 -Manufacturer#3 almond antique chartreuse khaki white 17 1 1 0.2 0.0 1 1 17.0 0.0 2 17 17 -Manufacturer#3 almond antique forest lavender goldenrod 14 2 2 0.4 0.25 1 2 15.5 1.5 2 14 17 -Manufacturer#3 almond antique metallic orange dim 19 3 3 0.6 0.5 2 3 16.666666666666668 2.0548046676563256 2 19 17 -Manufacturer#3 almond antique misty red olive 1 4 4 0.8 0.75 2 4 12.75 7.013380069552769 2 1 14 -Manufacturer#3 almond antique olive coral navajo 45 5 5 1.0 1.0 3 5 19.2 14.344336861632886 2 45 19 -Manufacturer#4 almond antique gainsboro frosted violet 10 1 1 0.2 0.0 1 1 10.0 0.0 0 10 10 -Manufacturer#4 almond antique violet mint lemon 39 2 2 0.4 0.25 1 2 24.5 14.5 0 39 10 -Manufacturer#4 almond aquamarine floral ivory bisque 27 3 3 0.6 0.5 2 3 25.333333333333332 11.897712198383164 0 27 10 -Manufacturer#4 almond aquamarine yellow dodger mint 7 4 4 0.8 0.75 2 4 20.75 13.007209539328564 0 7 39 -Manufacturer#4 almond azure aquamarine papaya violet 12 5 5 1.0 1.0 3 5 19.0 12.149074038789951 0 12 27 -Manufacturer#5 almond antique blue firebrick mint 31 1 1 0.2 0.0 1 1 31.0 0.0 1 31 31 -Manufacturer#5 almond antique medium spring khaki 6 2 2 0.4 0.25 1 2 18.5 12.5 1 6 31 -Manufacturer#5 almond antique sky peru orange 2 3 3 0.6 0.5 2 3 13.0 12.832251036613439 1 2 31 -Manufacturer#5 almond aquamarine dodger light gainsboro 46 4 4 0.8 0.75 2 4 21.25 18.102140757380052 1 46 6 -Manufacturer#5 almond azure blanched chiffon midnight 23 5 5 1.0 1.0 3 5 21.6 16.206171663906314 1 23 2 +Manufacturer#1 almond antique burnished rose metallic 2 1 1 0 0.0 1 2 2.0 0.0 2 2 2 +Manufacturer#1 almond antique burnished rose metallic 2 1 1 0 0.0 1 2 2.0 0.0 2 2 2 +Manufacturer#1 almond antique chartreuse lavender yellow 34 3 2 0 0.4 2 3 12.666666666666666 15.084944665313014 2 34 2 +Manufacturer#1 almond antique salmon chartreuse burlywood 6 4 3 0 0.6 2 4 11.0 13.379088160259652 2 6 2 +Manufacturer#1 almond aquamarine burnished black steel 28 5 4 0 0.8 3 5 14.4 13.763720427268202 2 28 34 +Manufacturer#1 almond aquamarine pink moccasin thistle 42 6 5 1 1.0 3 6 19.0 16.237815945091466 2 42 6 +Manufacturer#2 almond antique violet chocolate turquoise 14 1 1 0 0.0 1 1 14.0 0.0 4 14 14 +Manufacturer#2 almond antique violet turquoise frosted 40 2 2 0 0.25 1 2 27.0 13.0 4 40 14 +Manufacturer#2 almond aquamarine midnight light salmon 2 3 3 0 0.5 2 3 18.666666666666668 15.86050300449376 4 2 14 +Manufacturer#2 almond aquamarine rose maroon antique 25 4 4 0 0.75 2 4 20.25 14.00669482783144 4 25 40 +Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 5 5 1 1.0 3 5 19.8 12.560254774486067 4 18 2 +Manufacturer#3 almond antique chartreuse khaki white 17 1 1 0 0.0 1 1 17.0 0.0 2 17 17 +Manufacturer#3 almond antique forest lavender goldenrod 14 2 2 0 0.25 1 2 15.5 1.5 2 14 17 +Manufacturer#3 almond antique metallic orange dim 19 3 3 0 0.5 2 3 16.666666666666668 2.0548046676563256 2 19 17 +Manufacturer#3 almond antique misty red olive 1 4 4 0 0.75 2 4 12.75 7.013380069552769 2 1 14 +Manufacturer#3 almond antique olive coral navajo 45 5 5 1 1.0 3 5 19.2 14.344336861632886 2 45 19 +Manufacturer#4 almond antique gainsboro frosted violet 10 1 1 0 0.0 1 1 10.0 0.0 0 10 10 +Manufacturer#4 almond antique violet mint lemon 39 2 2 0 0.25 1 2 24.5 14.5 0 39 10 +Manufacturer#4 almond aquamarine floral ivory bisque 27 3 3 0 0.5 2 3 25.333333333333332 11.897712198383164 0 27 10 +Manufacturer#4 almond aquamarine yellow dodger mint 7 4 4 0 0.75 2 4 20.75 13.007209539328564 0 7 39 +Manufacturer#4 almond azure aquamarine papaya violet 12 5 5 1 1.0 3 5 19.0 12.149074038789951 0 12 27 +Manufacturer#5 almond antique blue firebrick mint 31 1 1 0 0.0 1 1 31.0 0.0 1 31 31 +Manufacturer#5 almond antique medium spring khaki 6 2 2 0 0.25 1 2 18.5 12.5 1 6 31 +Manufacturer#5 almond antique sky peru orange 2 3 3 0 0.5 2 3 13.0 12.832251036613439 1 2 31 +Manufacturer#5 almond aquamarine dodger light gainsboro 46 4 4 0 0.75 2 4 21.25 18.102140757380052 1 46 6 +Manufacturer#5 almond azure blanched chiffon midnight 23 5 5 1 1.0 3 5 21.6 16.206171663906314 1 23 2 PREHOOK: query: -- 16. testMultipleWindows select p_mfgr,p_name, p_size, rank() over(distribute by p_mfgr sort by p_name) as r, @@ -711,32 +711,32 @@ window w1 as (distribute by p_mfgr sort by p_mfgr, p_name rows between 2 precedi POSTHOOK: type: QUERY POSTHOOK: Input: default@part #### A masked pattern was here #### -Manufacturer#1 almond antique burnished rose metallic 2 1 1 0.3333333333333333 4 4 2 -Manufacturer#1 almond antique burnished rose metallic 2 1 1 0.3333333333333333 4 4 2 -Manufacturer#1 almond antique chartreuse lavender yellow 34 3 2 0.5 38 34 2 -Manufacturer#1 almond antique salmon chartreuse burlywood 6 4 3 0.6666666666666666 44 10 2 -Manufacturer#1 almond aquamarine burnished black steel 28 5 4 0.8333333333333334 72 28 34 -Manufacturer#1 almond aquamarine pink moccasin thistle 42 6 5 1.0 114 42 6 -Manufacturer#2 almond antique violet chocolate turquoise 14 1 1 0.2 14 14 14 -Manufacturer#2 almond antique violet turquoise frosted 40 2 2 0.4 54 40 14 -Manufacturer#2 almond aquamarine midnight light salmon 2 3 3 0.6 56 2 14 -Manufacturer#2 almond aquamarine rose maroon antique 25 4 4 0.8 81 25 40 -Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 5 5 1.0 99 32 2 -Manufacturer#3 almond antique chartreuse khaki white 17 1 1 0.2 17 31 17 -Manufacturer#3 almond antique forest lavender goldenrod 14 2 2 0.4 31 14 17 -Manufacturer#3 almond antique metallic orange dim 19 3 3 0.6 50 50 17 -Manufacturer#3 almond antique misty red olive 1 4 4 0.8 51 1 14 -Manufacturer#3 almond antique olive coral navajo 45 5 5 1.0 96 45 19 -Manufacturer#4 almond antique gainsboro frosted violet 10 1 1 0.2 10 17 10 -Manufacturer#4 almond antique violet mint lemon 39 2 2 0.4 49 39 10 -Manufacturer#4 almond aquamarine floral ivory bisque 27 3 3 0.6 76 27 10 -Manufacturer#4 almond aquamarine yellow dodger mint 7 4 4 0.8 83 7 39 -Manufacturer#4 almond azure aquamarine papaya violet 12 5 5 1.0 95 29 27 -Manufacturer#5 almond antique blue firebrick mint 31 1 1 0.2 31 31 31 -Manufacturer#5 almond antique medium spring khaki 6 2 2 0.4 37 8 31 -Manufacturer#5 almond antique sky peru orange 2 3 3 0.6 39 2 31 -Manufacturer#5 almond aquamarine dodger light gainsboro 46 4 4 0.8 85 46 6 -Manufacturer#5 almond azure blanched chiffon midnight 23 5 5 1.0 108 23 2 +Manufacturer#1 almond antique burnished rose metallic 2 1 1 0 4 4 2 +Manufacturer#1 almond antique burnished rose metallic 2 1 1 0 4 4 2 +Manufacturer#1 almond antique chartreuse lavender yellow 34 3 2 0 38 34 2 +Manufacturer#1 almond antique salmon chartreuse burlywood 6 4 3 0 44 10 2 +Manufacturer#1 almond aquamarine burnished black steel 28 5 4 0 72 28 34 +Manufacturer#1 almond aquamarine pink moccasin thistle 42 6 5 1 114 42 6 +Manufacturer#2 almond antique violet chocolate turquoise 14 1 1 0 14 14 14 +Manufacturer#2 almond antique violet turquoise frosted 40 2 2 0 54 40 14 +Manufacturer#2 almond aquamarine midnight light salmon 2 3 3 0 56 2 14 +Manufacturer#2 almond aquamarine rose maroon antique 25 4 4 0 81 25 40 +Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 5 5 1 99 32 2 +Manufacturer#3 almond antique chartreuse khaki white 17 1 1 0 17 31 17 +Manufacturer#3 almond antique forest lavender goldenrod 14 2 2 0 31 14 17 +Manufacturer#3 almond antique metallic orange dim 19 3 3 0 50 50 17 +Manufacturer#3 almond antique misty red olive 1 4 4 0 51 1 14 +Manufacturer#3 almond antique olive coral navajo 45 5 5 1 96 45 19 +Manufacturer#4 almond antique gainsboro frosted violet 10 1 1 0 10 17 10 +Manufacturer#4 almond antique violet mint lemon 39 2 2 0 49 39 10 +Manufacturer#4 almond aquamarine floral ivory bisque 27 3 3 0 76 27 10 +Manufacturer#4 almond aquamarine yellow dodger mint 7 4 4 0 83 7 39 +Manufacturer#4 almond azure aquamarine papaya violet 12 5 5 1 95 29 27 +Manufacturer#5 almond antique blue firebrick mint 31 1 1 0 31 31 31 +Manufacturer#5 almond antique medium spring khaki 6 2 2 0 37 8 31 +Manufacturer#5 almond antique sky peru orange 2 3 3 0 39 2 31 +Manufacturer#5 almond aquamarine dodger light gainsboro 46 4 4 0 85 46 6 +Manufacturer#5 almond azure blanched chiffon midnight 23 5 5 1 108 23 2 PREHOOK: query: -- 17. testCountStar select p_mfgr,p_name, p_size, count(*) over(distribute by p_mfgr sort by p_name ) as c, diff --git a/ql/src/test/results/clientpositive/windowing_rank.q.out b/ql/src/test/results/clientpositive/windowing_rank.q.out index 6a74a8e..7a4426f 100644 --- a/ql/src/test/results/clientpositive/windowing_rank.q.out +++ b/ql/src/test/results/clientpositive/windowing_rank.q.out @@ -268,106 +268,106 @@ POSTHOOK: query: select s, cume_dist() over (partition by bo order by b,s) from POSTHOOK: type: QUERY POSTHOOK: Input: default@over10k #### A masked pattern was here #### -calvin allen 2.0112630732099757E-4 -david ovid 4.0225261464199515E-4 -david zipper 6.033789219629927E-4 -ethan ellison 8.045052292839903E-4 -holly allen 0.001005631536604988 -irene garcia 0.0012067578439259854 -irene van buren 0.0014078841512469831 -jessica steinbeck 0.0016090104585679806 -katie xylophone 0.0018101367658889783 -mike xylophone 0.002011263073209976 -nick quirinius 0.0022123893805309734 -nick steinbeck 0.002413515687851971 -quinn steinbeck 0.002614641995172969 -rachel thompson 0.0028157683024939663 -sarah miller 0.0030168946098149637 -tom hernandez 0.003218020917135961 -ulysses ichabod 0.003419147224456959 -ulysses nixon 0.0036202735317779565 -ulysses xylophone 0.003821399839098954 -victor garcia 0.004022526146419952 -victor xylophone 0.004223652453740949 -wendy falkner 0.004424778761061947 -yuri nixon 0.004625905068382945 -bob johnson 0.004827031375703942 -bob king 0.00502815768302494 -calvin van buren 0.005229283990345938 -gabriella robinson 0.005430410297666935 -katie xylophone 0.0056315366049879325 -mike steinbeck 0.00583266291230893 -oscar quirinius 0.006033789219629927 -rachel davidson 0.006234915526950925 -sarah van buren 0.006436041834271922 -tom king 0.00663716814159292 -ulysses allen 0.006838294448913918 -wendy ellison 0.007039420756234915 -zach allen 0.007240547063555913 -zach young 0.007441673370876911 -alice falkner 0.007642799678197908 -bob ovid 0.007843925985518906 -bob underhill 0.008045052292839904 -ethan ovid 0.008246178600160902 -gabriella davidson 0.008447304907481898 -gabriella garcia 0.008648431214802896 -irene nixon 0.008849557522123894 -jessica brown 0.009050683829444892 -jessica miller 0.00925181013676589 -jessica quirinius 0.009452936444086887 -luke falkner 0.009654062751407884 -luke robinson 0.009855189058728881 -mike steinbeck 0.01005631536604988 -mike van buren 0.010257441673370877 -priscilla hernandez 0.010458567980691875 -tom polk 0.010659694288012871 -ulysses king 0.01086082059533387 -ulysses robinson 0.011061946902654867 -xavier davidson 0.011263073209975865 -alice hernandez 0.011464199517296863 -bob underhill 0.01166532582461786 -calvin nixon 0.011866452131938857 -david davidson 0.012067578439259855 -holly falkner 0.012268704746580853 -irene laertes 0.01246983105390185 -jessica robinson 0.012670957361222849 -mike falkner 0.012872083668543845 -nick falkner 0.013073209975864843 -oscar laertes 0.01327433628318584 -oscar miller 0.013475462590506838 -oscar thompson 0.013676588897827836 -priscilla nixon 0.013877715205148834 -priscilla xylophone 0.01407884151246983 -quinn miller 0.014279967819790828 -victor robinson 0.014481094127111826 -wendy allen 0.014682220434432824 -wendy nixon 0.014883346741753822 -yuri ellison 0.015084473049074818 -calvin nixon 0.015285599356395816 -fred carson 0.015486725663716814 -holly davidson 0.015687851971037812 -irene king 0.01588897827835881 -jessica davidson 0.016090104585679808 -katie polk 0.016492357200321803 -katie polk 0.016492357200321803 -luke johnson 0.0166934835076428 -nick allen 0.016894609814963796 -nick ellison 0.017095736122284794 -oscar king 0.01729686242960579 -priscilla laertes 0.01749798873692679 -priscilla underhill 0.017699115044247787 -priscilla young 0.017900241351568785 -victor steinbeck 0.018101367658889783 -wendy miller 0.01830249396621078 -calvin carson 0.01850362027353178 -ethan hernandez 0.018704746580852777 -ethan laertes 0.01910699919549477 -ethan laertes 0.01910699919549477 -ethan white 0.019308125502815767 -fred ellison 0.019509251810136765 -gabriella hernandez 0.019710378117457763 -gabriella ovid 0.01991150442477876 -gabriella steinbeck 0.02011263073209976 +calvin allen NULL +david ovid NULL +david zipper NULL +ethan ellison NULL +holly allen 0 +irene garcia 0 +irene van buren 0 +jessica steinbeck 0 +katie xylophone 0 +mike xylophone 0 +nick quirinius 0 +nick steinbeck 0 +quinn steinbeck 0 +rachel thompson 0 +sarah miller 0 +tom hernandez 0 +ulysses ichabod 0 +ulysses nixon 0 +ulysses xylophone 0 +victor garcia 0 +victor xylophone 0 +wendy falkner 0 +yuri nixon 0 +bob johnson 0 +bob king 0 +calvin van buren 0 +gabriella robinson 0 +katie xylophone 0 +mike steinbeck 0 +oscar quirinius 0 +rachel davidson 0 +sarah van buren 0 +tom king 0 +ulysses allen 0 +wendy ellison 0 +zach allen 0 +zach young 0 +alice falkner 0 +bob ovid 0 +bob underhill 0 +ethan ovid 0 +gabriella davidson 0 +gabriella garcia 0 +irene nixon 0 +jessica brown 0 +jessica miller 0 +jessica quirinius 0 +luke falkner 0 +luke robinson 0 +mike steinbeck 0 +mike van buren 0 +priscilla hernandez 0 +tom polk 0 +ulysses king 0 +ulysses robinson 0 +xavier davidson 0 +alice hernandez 0 +bob underhill 0 +calvin nixon 0 +david davidson 0 +holly falkner 0 +irene laertes 0 +jessica robinson 0 +mike falkner 0 +nick falkner 0 +oscar laertes 0 +oscar miller 0 +oscar thompson 0 +priscilla nixon 0 +priscilla xylophone 0 +quinn miller 0 +victor robinson 0 +wendy allen 0 +wendy nixon 0 +yuri ellison 0 +calvin nixon 0 +fred carson 0 +holly davidson 0 +irene king 0 +jessica davidson 0 +katie polk 0 +katie polk 0 +luke johnson 0 +nick allen 0 +nick ellison 0 +oscar king 0 +priscilla laertes 0 +priscilla underhill 0 +priscilla young 0 +victor steinbeck 0 +wendy miller 0 +calvin carson 0 +ethan hernandez 0 +ethan laertes 0 +ethan laertes 0 +ethan white 0 +fred ellison 0 +gabriella hernandez 0 +gabriella ovid 0 +gabriella steinbeck 0 PREHOOK: query: select s, percent_rank() over (partition by dec order by f) from over10k limit 100 PREHOOK: type: QUERY PREHOOK: Input: default@over10k diff --git a/ql/src/test/results/clientpositive/windowing_streaming.q.out b/ql/src/test/results/clientpositive/windowing_streaming.q.out index f4afbe0..4bd014e 100644 --- a/ql/src/test/results/clientpositive/windowing_streaming.q.out +++ b/ql/src/test/results/clientpositive/windowing_streaming.q.out @@ -63,7 +63,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: part + alias: a:part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) @@ -73,32 +73,32 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col1, _col2 + outputColumnNames: p_name, p_mfgr Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col1: string, _col2: string + output shape: p_name: string, p_mfgr: string type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col1 - partition by: _col2 + order by: p_name + partition by: p_mfgr raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col1 + alias: $win$_col_164 + arguments: p_name name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), rank_window_0 (type: int) - outputColumnNames: _col0, _col1 + expressions: p_mfgr (type: string), $win$_col_164 (type: int) + outputColumnNames: p_mfgr, rank_window_0 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -133,7 +133,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: part + alias: a:part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) @@ -144,35 +144,35 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col1, _col2 + outputColumnNames: p_name, p_mfgr Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col1: string, _col2: string + output shape: p_name: string, p_mfgr: string type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col1 - partition by: _col2 + order by: p_name + partition by: p_mfgr raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col1 + alias: $win$_col_165 + arguments: p_name name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (rank_window_0 < 4) (type: boolean) + predicate: ($win$_col_165 < 4) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: string), rank_window_0 (type: int) - outputColumnNames: _col0, _col1 + expressions: p_mfgr (type: string), $win$_col_165 (type: int) + outputColumnNames: p_mfgr, rank_window_0 Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -302,7 +302,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: alltypesorc + alias: a:alltypesorc Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: ctinyint (type: tinyint), cdouble (type: double) @@ -313,35 +313,35 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double) - outputColumnNames: _col0, _col5 + outputColumnNames: ctinyint, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col0: tinyint, _col5: double + output shape: ctinyint: tinyint, cdouble: double type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col5 - partition by: _col0 + order by: cdouble + partition by: ctinyint raw input shape: window functions: window function definition - alias: rank_window_0 - arguments: _col5 + alias: $win$_col_169 + arguments: cdouble name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (rank_window_0 < 5) (type: boolean) + predicate: ($win$_col_169 < 5) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: tinyint), _col5 (type: double), rank_window_0 (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: ctinyint (type: tinyint), cdouble (type: double), $win$_col_169 (type: int) + outputColumnNames: ctinyint, cdouble, rank_window_0 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false