diff --git itests/src/test/resources/testconfiguration.properties itests/src/test/resources/testconfiguration.properties index a0829a1..3909994 100644 --- itests/src/test/resources/testconfiguration.properties +++ itests/src/test/resources/testconfiguration.properties @@ -388,6 +388,7 @@ spark.query.files=alter_merge_orc.q \ sample5.q \ sample6.q \ sample7.q \ + sample8.q \ sample9.q \ sort.q \ spark_test.q \ diff --git ql/src/test/results/clientpositive/spark/sample8.q.out ql/src/test/results/clientpositive/spark/sample8.q.out new file mode 100644 index 0000000..c7e333b --- /dev/null +++ ql/src/test/results/clientpositive/spark/sample8.q.out @@ -0,0 +1,981 @@ +PREHOOK: query: -- sampling with join and alias +-- SORT_QUERY_RESULTS + +EXPLAIN EXTENDED +SELECT s.* +FROM srcpart TABLESAMPLE (BUCKET 1 OUT OF 1 ON key) s +JOIN srcpart TABLESAMPLE (BUCKET 1 OUT OF 10 ON key) t +WHERE t.key = s.key and t.value = s.value and s.ds='2008-04-08' and s.hr='11' +PREHOOK: type: QUERY +POSTHOOK: query: -- sampling with join and alias +-- SORT_QUERY_RESULTS + +EXPLAIN EXTENDED +SELECT s.* +FROM srcpart TABLESAMPLE (BUCKET 1 OUT OF 1 ON key) s +JOIN srcpart TABLESAMPLE (BUCKET 1 OUT OF 10 ON key) t +WHERE t.key = s.key and t.value = s.value and s.ds='2008-04-08' and s.hr='11' +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + +TOK_QUERY + TOK_FROM + TOK_JOIN + TOK_TABREF + TOK_TABNAME + srcpart + TOK_TABLEBUCKETSAMPLE + 1 + 1 + TOK_TABLE_OR_COL + key + s + TOK_TABREF + TOK_TABNAME + srcpart + TOK_TABLEBUCKETSAMPLE + 1 + 10 + TOK_TABLE_OR_COL + key + t + TOK_INSERT + TOK_DESTINATION + TOK_DIR + TOK_TMP_FILE + TOK_SELECT + TOK_SELEXPR + TOK_ALLCOLREF + TOK_TABNAME + s + TOK_WHERE + and + and + and + = + . + TOK_TABLE_OR_COL + t + key + . + TOK_TABLE_OR_COL + s + key + = + . + TOK_TABLE_OR_COL + t + value + . + TOK_TABLE_OR_COL + s + value + = + . + TOK_TABLE_OR_COL + s + ds + '2008-04-08' + = + . + TOK_TABLE_OR_COL + s + hr + '11' + + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP SORT), Map 3 (GROUP SORT) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t + Statistics: Num rows: 116 Data size: 23248 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: true + predicate: ((((((hash(key) & 2147483647) % 1) = 0) and key is not null) and value is not null) and (((hash(key) & 2147483647) % 10) = 0)) (type: boolean) + Statistics: Num rows: 7 Data size: 1402 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: 7 Data size: 1402 Basic stats: COMPLETE Column stats: NONE + tag: 1 + auto parallelism: true + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### 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 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns key,value + columns.comments defaultdefault + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows -1 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize -1 + 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 defaultdefault + 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 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns key,value + columns.comments defaultdefault + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows -1 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize -1 + 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 defaultdefault + 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=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 false + bucket_count -1 + columns key,value + columns.comments defaultdefault + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows -1 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize -1 + 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 defaultdefault + 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 false + bucket_count -1 + columns key,value + columns.comments defaultdefault + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows -1 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize -1 + 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 defaultdefault + 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 [t] + /srcpart/ds=2008-04-08/hr=12 [t] + /srcpart/ds=2008-04-09/hr=11 [t] + /srcpart/ds=2008-04-09/hr=12 [t] + Map 3 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: true + predicate: ((((((hash(key) & 2147483647) % 10) = 0) and key is not null) and value is not null) and (((hash(key) & 2147483647) % 1) = 0)) (type: boolean) + Statistics: Num rows: 2 Data size: 400 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: 2 Data size: 400 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: ds (type: string), hr (type: string) + auto parallelism: true + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### 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 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns key,value + columns.comments defaultdefault + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows -1 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize -1 + 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 defaultdefault + 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 [s] + Reducer 2 + Needs Tagging: true + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {KEY.reducesinkkey1} {VALUE._col0} {VALUE._col1} + 1 {KEY.reducesinkkey0} {KEY.reducesinkkey1} + outputColumnNames: _col0, _col1, _col2, _col3, _col7, _col8 + Statistics: Num rows: 7 Data size: 1542 Basic stats: COMPLETE Column stats: NONE + Filter Operator + isSamplingPred: false + predicate: ((((_col7 = _col0) and (_col8 = _col1)) and (_col2 = '2008-04-08')) and (_col3 = '11')) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), '11' (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 + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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.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 + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s.key, s.value +FROM srcpart TABLESAMPLE (BUCKET 1 OUT OF 1 ON key) s +JOIN srcpart TABLESAMPLE (BUCKET 1 OUT OF 10 ON key) t +WHERE t.key = s.key and t.value = s.value and s.ds='2008-04-08' and s.hr='11' +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 s.key, s.value +FROM srcpart TABLESAMPLE (BUCKET 1 OUT OF 1 ON key) s +JOIN srcpart TABLESAMPLE (BUCKET 1 OUT OF 10 ON key) t +WHERE t.key = s.key and t.value = s.value and s.ds='2008-04-08' and s.hr='11' +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 #### +105 val_105 +105 val_105 +105 val_105 +105 val_105 +114 val_114 +114 val_114 +114 val_114 +114 val_114 +150 val_150 +150 val_150 +150 val_150 +150 val_150 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +178 val_178 +178 val_178 +178 val_178 +178 val_178 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +187 val_187 +196 val_196 +196 val_196 +196 val_196 +196 val_196 +2 val_2 +2 val_2 +2 val_2 +2 val_2 +213 val_213 +213 val_213 +213 val_213 +213 val_213 +213 val_213 +213 val_213 +213 val_213 +213 val_213 +213 val_213 +213 val_213 +213 val_213 +213 val_213 +213 val_213 +213 val_213 +213 val_213 +213 val_213 +222 val_222 +222 val_222 +222 val_222 +222 val_222 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +286 val_286 +286 val_286 +286 val_286 +286 val_286 +321 val_321 +321 val_321 +321 val_321 +321 val_321 +321 val_321 +321 val_321 +321 val_321 +321 val_321 +321 val_321 +321 val_321 +321 val_321 +321 val_321 +321 val_321 +321 val_321 +321 val_321 +321 val_321 +367 val_367 +367 val_367 +367 val_367 +367 val_367 +367 val_367 +367 val_367 +367 val_367 +367 val_367 +367 val_367 +367 val_367 +367 val_367 +367 val_367 +367 val_367 +367 val_367 +367 val_367 +367 val_367 +394 val_394 +394 val_394 +394 val_394 +394 val_394 +402 val_402 +402 val_402 +402 val_402 +402 val_402 +411 val_411 +411 val_411 +411 val_411 +411 val_411 +439 val_439 +439 val_439 +439 val_439 +439 val_439 +439 val_439 +439 val_439 +439 val_439 +439 val_439 +439 val_439 +439 val_439 +439 val_439 +439 val_439 +439 val_439 +439 val_439 +439 val_439 +439 val_439 +448 val_448 +448 val_448 +448 val_448 +448 val_448 +457 val_457 +457 val_457 +457 val_457 +457 val_457 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +466 val_466 +475 val_475 +475 val_475 +475 val_475 +475 val_475 +484 val_484 +484 val_484 +484 val_484 +484 val_484 +493 val_493 +493 val_493 +493 val_493 +493 val_493 +77 val_77 +77 val_77 +77 val_77 +77 val_77 +86 val_86 +86 val_86 +86 val_86 +86 val_86 +95 val_95 +95 val_95 +95 val_95 +95 val_95 +95 val_95 +95 val_95 +95 val_95 +95 val_95 +95 val_95 +95 val_95 +95 val_95 +95 val_95 +95 val_95 +95 val_95 +95 val_95 +95 val_95 +PREHOOK: query: EXPLAIN +SELECT * FROM src TABLESAMPLE(100 ROWS) a JOIN src1 TABLESAMPLE(10 ROWS) b ON a.key=b.key +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT * FROM src TABLESAMPLE(100 ROWS) a JOIN src1 TABLESAMPLE(10 ROWS) b ON a.key=b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP SORT), Map 3 (GROUP SORT) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Row Limit Per Split: 10 + Statistics: Num rows: 1 Data size: 216 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 216 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: 216 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + Row Limit Per Split: 100 + Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 15 Data size: 3006 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: 15 Data size: 3006 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 16 Data size: 3306 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 16 Data size: 3306 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 16 Data size: 3306 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.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 + +PREHOOK: query: SELECT * FROM src TABLESAMPLE(100 ROWS) a JOIN src1 TABLESAMPLE(10 ROWS) b ON a.key=b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM src TABLESAMPLE(100 ROWS) a JOIN src1 TABLESAMPLE(10 ROWS) b ON a.key=b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +238 val_238 238 val_238 +255 val_255 255 val_255 +278 val_278 278 val_278 +311 val_311 311 val_311 +311 val_311 311 val_311 +98 val_98 98 val_98 +PREHOOK: query: EXPLAIN +SELECT * FROM src TABLESAMPLE(100 ROWS) a, src1 TABLESAMPLE(10 ROWS) b WHERE a.key=b.key +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT * FROM src TABLESAMPLE(100 ROWS) a, src1 TABLESAMPLE(10 ROWS) b WHERE a.key=b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP SORT), Map 3 (GROUP SORT) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Row Limit Per Split: 10 + Statistics: Num rows: 1 Data size: 216 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 216 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: 216 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + Row Limit Per Split: 100 + Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 15 Data size: 3006 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: 15 Data size: 3006 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 16 Data size: 3306 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col0 = _col5) (type: boolean) + Statistics: Num rows: 8 Data size: 1653 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 8 Data size: 1653 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 8 Data size: 1653 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.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 + +PREHOOK: query: SELECT * FROM src TABLESAMPLE(100 ROWS) a, src1 TABLESAMPLE(10 ROWS) b WHERE a.key=b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM src TABLESAMPLE(100 ROWS) a, src1 TABLESAMPLE(10 ROWS) b WHERE a.key=b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +238 val_238 238 val_238 +255 val_255 255 val_255 +278 val_278 278 val_278 +311 val_311 311 val_311 +311 val_311 311 val_311 +98 val_98 98 val_98